2. Brain Organisation

On the model presented here, the brain is organised as a supervenience hierarchy, such that higher levels of organisation emerge from interactions at lower levels of organisation during development and experience. There is no interaction between levels; for example, higher levels of organisation do not control lower levels — ‘downward causation’ — any more than a clock controls the molecules on which it supervenes as a level of organisation, because levels of organisation are complementary perspectives on the same phenomenon. On the TNGS model, the notion of ‘control’ is better reinterpreted in terms of selectional interaction between systems at the same level of organisation, if only because it is a ‘category error’ to map a hierarchy of degrees of control onto a hierarchy of organisational levels. 

In considering interactions between systems at the same level of organisation, each system is necessary but not sufficient for the function it performs, just as a specific gene, as “for” iris colour, is necessary but not sufficient for its function (phenotypic expression); a gene only functions in the context of (the functions of) other genes, and its function is distinguished by contrast with the functions of other genes in the genome. Similarly, neurological functions are carried out in the context of other functions and each function is distinguished by contrast with those other functions. Absence or disruption of a specific function results from the absence or disruption of a necessary condition for its performance, as the absence or mutation of a gene results in the absence or variation of its phenotypic expression. By identifying loss of brain function with localised anatomical damage, some have argued that those functions are carried out in those areas, as if such areas are sufficient for the function. However, as brain imaging shows, even for something as “simple” as reciting digits, neural activity is distributed over many regions the brain, and the precise locations of activity vary from one individual to the next.

ChatGPT said:

The Brain as a Supervenience Hierarchy: A Reinterpretation of 'Control' and Function

In the model presented here, the brain is organised as a supervenience hierarchy, where higher levels of organisation emerge from the interactions at lower levels during development and experience. Crucially, there is no direct interaction between these levels. Higher levels of organisation do not "control" lower levels—a concept often referred to as "downward causation"—any more than a clock controls the molecules it supervenes upon as a level of organisation. Both higher and lower levels of organisation provide complementary perspectives on the same underlying phenomenon, rather than representing a relationship of control.

This interpretation challenges traditional notions of control in neurological systems. On the Theory of Neuronal Group Selection (TNGS) model, the idea of control is better understood in terms of selectional interaction between systems within the same level of organisation, rather than imposing a hierarchy of control across organisational levels. The suggestion that higher levels exert downward control over lower levels represents a category error: applying a hierarchy of control to a hierarchy of organisational levels distorts the nature of how systems interact within those levels.

When we consider interactions at the same level of organisation, each system is necessary for the function it performs, but not sufficient in isolation. For example, a gene associated with iris colour is necessary but not sufficient for the expression of that colour in a phenotype. Its function is dependent on the context provided by other genes and their own functions within the broader genetic system. The same principle applies to neurological functions: they are carried out within the context of other functions, and each function is distinguished by its relationship to other functions within the network. The absence or disruption of a specific function is due to the absence or disruption of a necessary condition for its performance, much like the absence or mutation of a gene alters its phenotypic expression.

Some have argued that specific brain functions are localised to certain anatomical areas, based on the idea that the presence or absence of brain activity in those areas directly corresponds to the presence or absence of function. However, neuro-imaging studies demonstrate that even simple tasks, such as reciting digits, involve the activation of multiple brain regions. The precise locations of this neural activity can vary between individuals, challenging the notion that specific brain functions are exclusively confined to distinct anatomical regions. The brain's functioning is thus distributed and dynamic, and its organisation should be understood not in terms of rigid localisation, but as a complex interplay of systems interacting at multiple levels.

1. Brain: Biology Or Technology?

Historically, the neurological system has been frequently modelled as if it were a technological artefact. For example, the brain has been modelled as if it were a factory production line, and more recently as a computer, with inputs being “processed” in one section or module, creating outputs which then become inputs for other sections or modules; nerve fibres have been modelled as if they are the wires of a telephone network, carrying “messages” from one region to another[1]; and memory has been modelled as if was a storage location from which information is “retrieved”, or “accessed”, and acted upon, first as if it were an office filing system, and more latterly as if it were a place in a computer: “information is stored in memory”.

Using technology as a model for the neurological system is an example of semiotic generalisation[2], in the sense used in previous chapters, namely: meanings evolved in one context spread into another where they are proffered for selection. But given that neurological systems are phenotypic products of biological evolution and technological systems are phenotypic products of semiotic evolution, a more self-consistent and parsimonious approach would be to apply biological models to phenomena deemed to be biological systems, as Edelman (1989) has done with his Theory of Neuronal Group Selection (TNGS).[3] Biological models of biological phenomena are more likely to survive longterm semiotic selection than other models, if only because they are smaller innovations — just as smaller genetic innovations are more likely to survive biological selection. Selection against the technological model of the brain occurs, inter alia, every time a specialist in the field decides that the cost of the approach exceeds its benefits in terms of experiential consistency.[4]

Footnotes:

[1] Where this model is used, there is often a failure to distinguish between information as the flow of electro-chemical difference in neural circuits and information in the sense of categories of experience arising from a substrate of brain activity in individuals in ecosystems that include social-semiotic contexts. 

[2] In the field of cognitive linguistics, this mapping of the relations of a ‘source’ domain (here: technology) onto a ‘target’ domain (here: neurology) is known as conceptual metaphor. The mapping here is within the larger mapping of ‘an organism is a machine’: ‘a brain is a computer (that processes inputs, such as language)’, ‘a brain region is a processing unit’, ‘nerve fibres are communication lines’, and so on. 

[3] Compare Einstein’s maxim that the best model of a duck is a duck, and if possible, the same duck. 

[4] See the discussion of ‘truth’ later in this chapter.

ChatGPT said:

Technological Models of the Brain: A Semiotic Generalisation

Historically, neurological systems have often been understood through the lens of technological artefacts. From the brain as a factory production line to more recent conceptualisations of it as a computer, these models have sought to map the brain’s workings onto familiar human-made systems. For example, nerve fibres have been likened to wires in a telephone network, conveying "messages" between brain regions; memory has been compared to a storage system, with information "retrieved" when needed; and the brain itself is sometimes treated as a processing unit that handles inputs and outputs in a manner analogous to a computer's functionality.

This analogy of the brain as a machine, drawing from the technological world, is an example of semiotic generalisation. As discussed in earlier chapters, semiotic generalisation refers to the process by which meanings that arise in one context are extended to another. In this case, the structure and function of technology are mapped onto the brain, offering a convenient, if imperfect, metaphor. However, there is an important distinction to make: while neurological systems are biological products of evolution, technological systems are human-made constructs. Given the differences between biological and technological phenomena, a more consistent and parsimonious approach would be to use biological models to understand neurological systems—such as Edelman’s Theory of Neuronal Group Selection (TNGS), which accounts for the brain's complexity in a way that is more consistent with evolutionary biology.

This move towards biological models aligns with the principles of biological selection, which, much like the process that shapes living organisms, favours smaller, more adaptive innovations over time. Technological models of the brain, while sometimes useful for providing a framework, often encounter limitations as they fail to reflect the full complexity and evolutionary origins of neural systems. In the long run, these models are less likely to hold up under semiotic selection, especially as they are often at odds with the brain’s fundamental biological processes. Selection against the technological metaphor occurs every time it becomes clear that it doesn't adequately capture the brain’s operations, particularly when more biologically grounded models provide better explanatory power.

This isn’t to dismiss the technological metaphors entirely—they have served as useful stepping stones in the development of neurological theory. But as we understand more about the brain’s evolution and functionality, it becomes apparent that the technological metaphors are increasingly inadequate, and that a biological model offers a far richer and more sustainable explanation.

4 The Perceivable Is Unlabelled

Gardner (1970: 227): 

The realisation that the world by itself contains no signs — that there is no connection whatever between things and their names except by way of a mind that finds the tags useful — is by no means a trivial philosophic insight. 

On this model, the perceivable[1] world isn’t labelled for categories, but it is of survival value to organisms to categorise the world in some ways rather than others. The perceivable world favours (selects) some ways of categorising over others, varying for species, but it does not follow from this that it contains categories independent of a categorising process. 

The contexts in which organisms are embedded are categorisable; they are recognition potential. From the perspective of categorisation, such domains are potential: they have, for example, the potential to kill, to end the categorising. They are a flux of varying probability. 

Categorising arises from interactions between, on the one hand, domains that can be categorised, that involve difference (information), and on the other, systems that can categorise.[2] Domains that can be categorised are differentiable: they have the potential to be differentiated by a categorising system. To experience a perceivable context is to differentiate it. The perceivable is both “experienceable”: categorisable and “act-upon-able”, and experienced: categorised and acted-upon. 

Footnotes:

[1] Note that using the word phenomenon for ‘a perceivable’ would be confusing here. The (nontechnical) meaning is ‘a fact, occurrence, or circumstance observed or observable’ (Macquarie Dictionary 1992:1329), while Kant distinguishes phenomenon: ‘a thing as it appears to and is constructed by us’, from noumenon ‘a thing in itself’ (ibid).

[2] Strictly speaking, perceiving is an interaction between the universe of difference (in general) being perceived and a part of that difference (perceived by the modeller to be) organised as a categoriser and doing the perceiving.

ChatGPT said:

Categorisation, Survival, and the Perceivable World

“The realisation that the world by itself contains no signs — that there is no connection whatever between things and their names except by way of a mind that finds the tags useful — is by no means a trivial philosophic insight.”
— Gardner (1970: 227)

On this model, the world is not inherently labelled for categorisation. There are no tags written into the fabric of reality. Yet it is of survival value for organisms to categorise the world in particular ways, and not others. The perceivable world exerts selective pressure: it favours some forms of categorisation over others, depending on the species and its ecological niche. But it does not follow from this that categories exist independently of the categorising processes that bring them forth.

The contexts in which organisms are embedded are not already categorised—they are categorisable. They offer recognition potential. From the perspective of categorisation, such domains are potential: they hold the possibility of being differentiated, responded to, even survived. They are not neutral; they are active fields of affordance—structured but indeterminate, a flux of varying probability.

Categorisation arises through the interaction between two systems: one, a domain that can be differentiated (a universe of difference), and the other, a system capable of differentiation (a categoriser). A categorisable domain contains information in the form of difference; it can be acted upon and experienced. To experience a perceivable context is to differentiate it. The perceivable is both that which can be experienced and acted upon, and that which is experienced and acted upon. It is at once potential and instance.

---

Footnotes:

[1] The term perceivable is preferred here over phenomenon. In everyday usage, phenomenon refers to a fact, occurrence, or circumstance that is observed or observable (Macquarie Dictionary, 1992:1329). However, in Kantian terms, a phenomenon is a thing as it appears to and is constructed by us, in contrast with the noumenon, or thing-in-itself. To avoid these associations, perceivable is used to refer to a domain available for perceptual interaction, but not yet categorised.

[2] More precisely, perception is an interaction between the general universe of difference and a subsystem of that universe—organised (from the modeller’s perspective) as a categoriser—that acts to differentiate it.

3. The Categorisable And The Categorising Are Distinct

A domain that can be categorised is distinct from any categorising of it.[1] Categories are not “out there” to be discovered, but are established through the interaction of recognition systems with a categorisable domain, which potentially includes the categorising processes themselves. The categorisable domain is potential, the categorising is a process. 

Footnote:

[1] Models don’t “construct reality” — they are organisations of categorisations of the categorisable. All models are organisations of categorisations, not of the categorisable.

ChatGPT said:

Categorisation and the Distinction Between Process and Potential

A domain that can be categorised is distinct from any act of categorising it. Categories are not inherent properties of the world waiting to be discovered; rather, they are established through the interaction between recognition systems and a domain that affords categorisation. This domain includes not only the phenomena to be categorised but potentially the categorising processes themselves. The categorisable domain is potential; categorisation is a process.

This distinction underscores a crucial point: models do not “construct reality”. Rather, they are organisations of categorisations—structured ways of interpreting what can be categorised. All models organise not the world itself, but the ways in which it is rendered intelligible through acts of categorisation. They are meta-structures, shaped by recognition systems engaging with the potential for structure.

7. How Difference Is Correlated

In the selectionist model of biological evolution proposed by Darwin and Wallace, Nature selects some variants (potentials) at the expense of others, depending on how well each functions in the contexts in which they have to function. These variants are the ones most likely to "happen again" in the next generation. In the selectionist model of brain function proposed by Edelman, the TNGS, in perceptual categorisation, the perceivable selects some variant neural events (potentials) at the expense of others. Selection involves the strengthening of synaptic connections between neurons in groups in maps, thereby increasing the probability that such configurations will fire again. These neural variants are the ones most likely to "happen again" in the next generation of neural firing in response to specific sensory detections of difference. 

This model can be understood in terms of the grammatical concept of ergativity: each perceptual categorising process is actualised through a medium, a brain as neurological recognition system, and caused by an external agent, a domain that can be detected and categorised.[1]

Note, by the way, that this is in stark contrast to an understanding based on the grammatical concept of transitivity. On such a model, a categorising process carries through from an actor, an external domain, to a goal, a brain as neurological recognition system. That is to say, categories flow into brains from the outside. Edelman (1992) labels this position instructionism since it involves seeing categorisation as a process whereby the outside instructs the brain, and he opposes it to selectionism, pointing out that instructionism is Lamarckism applied to the brain.[2] In the Lamarckian model of biological evolution, properties flow from the world into genomes, such that acquired characteristics can be inherited by offspring. That is, a coded world acts directly on a specific genome and changes it. 

There are probably many reasons why the instructionist/transitive model should have been previously favoured in modelling the brain. For example, it is more obviously recognisable from visual experience: we see that things move from one location to another.[3] Selectionism is more subtle, since it requires a generational timescale to observe the effects of selection in a visible domain. The view of human-as-agent may also have made the acceptance of the phenomenon-as-agent model less probable. 

Footnotes:

[1] Phenomena make us sense: see, hear, smell, taste, feel (perception); phenomena make us feel (affect); phenomena make us think (cognition); phenomena make us want (desideration).

[2] Instructionism fails to explain, for example, why a patient of (Oliver) Sacks, ‘Virgil’, who receives sight for the first time at age 50 cannot make sense of what he sees.

[3] Cf Lakoff’s (1987) source-path-goal schema.

ChatGPT said:

Selectionism, Categorisation, and the Grammar of Causation

In Darwin and Wallace’s selectionist model of evolution, Nature selects among variant potentials depending on how effectively they function in the contexts in which they must operate. Those variants that function better are more likely to “happen again” in subsequent generations. Edelman’s Theory of Neuronal Group Selection (TNGS) applies this logic to brain function: in perceptual categorisation, it is the perceivable that selects among variant neural events. Neural variants are actualised through the strengthening of synaptic connections between neurons in neural maps, thereby increasing the probability that similar configurations will fire again in response to comparable sensory inputs. These variants, like biological ones, are those most likely to “happen again” — not in reproductive generations, but in the next generation of neural firings.

This selectionist model can be usefully understood in terms of the grammatical concept of ergativity: the categorising process is actualised through a medium — the brain, as neurological recognition system — but caused by an external agent — the domain to be categorised.[1] The perceivable acts upon the brain by selecting which of its potentials are reinforced.

This stands in stark contrast to a transitive grammatical model of causation, where the process carries through from an Actor (external domain) to a Goal (the brain), as if categories are transmitted into the brain from the outside. This is the model Edelman (1992) calls instructionism, in which the external world is presumed to instruct the brain. Instructionism is effectively Lamarckism for the brain: it treats the world as already coded and the brain as its passive receiver. Just as Lamarck’s evolutionary theory imagined acquired traits being inscribed onto the genome, instructionism imagines that the categorised world imprints itself directly onto the neural substrate.

The prevalence of this model likely stems from intuitive biases. For one, it aligns with the visual metaphysics of movement: we can see things move from one place to another, so we project a similar structure onto causation in perception.[3] Selectionism, by contrast, is less intuitively accessible. It requires an understanding of cumulative effects across generational cycles of neural activation — a process we do not directly perceive. The longstanding image of the human as the locus of agency may also have made it harder to accept a model in which phenomena themselves act: where external difference is the initiating force and the brain the responsive medium.[2]

6. Perceiving As Correlating Difference

The general principle of a recognition system is the if…then relation: if event x in the recognisable domain, then event y in the recognition system. Recognition by neurological systems involves matching categorisables with neuronal activities that categorise. For perception, this means correlating difference (information) outside the system with difference (information) inside the system. The identity of any categorising activity within the system is given, therefore, by contrast to the other categorising activities within the system. Each categorising has no meaning without reference to other categorising.

ChatGPT said:

Recognition Systems and the Relational Nature of Categorising

The general principle of a recognition system is the if…then relation:
If event x occurs in the recognisable domain, then event y occurs in the recognition system.

In neurological systems, recognition entails the systematic correlation of categorisables with neural activities that categorise. For perception, this means correlating difference (i.e. information) external to the system with difference internal to it. Categorisation is not the passive registration of pre-existing properties but the activation of internal differentiations in response to external differentiability.

Crucially, the identity of any categorising activity within the system is not absolute but relational: it is defined by contrast with other categorising activities within the same system. A categorisation has no meaning in isolation. Each is part of a structured network of possible distinctions, and it is only within that network — through its systemic contrast with others — that it acquires identity.

This aligns with the principle that categories are not discovered but made: they are constituted through systemic relations among categorisings, not through a one-to-one mapping of internal signs onto external essences.

5. The Participants In The Categorisation Process

The categorisation process is a systematic interaction between: 

(1) the perceivable: what can be detected and categorised; 

(2) a means of detecting the categorisable, specifically: light in the case of visual perception[1]; and 

(3) a recognition system that can categorise what it can detect through sensory modalities like vision, hearing, smell, taste, touch. 

The distinction between (1) and (2) does not hold for all sensory modalities. For example, in the case of touch, there is no intermediary between the perceivable surface and the tactile sensory detectors. The same is true for taste, where there is no intermediary between the perceivable chemicals and the olfactory sensory detectors. In the case of smell, there is no intermediary between the perceivable chemicals and the olfactory sensory detectors, but the perceivable chemicals may emanate from a source that is not otherwise directly perceivable. This is also the case for hearing: there is no intermediary between the perceivable air compression waves and the auditory sensory detectors, but the perceivable air compression waves may emanate from a source that is not otherwise directly perceivable. 

Crucially, the distinction does hold for the primary modality of humans: vision. Visual perception does involve an intermediary between the perceivable and the visual sensory detectors. What makes contact with the sensory modalities, photons, is distinct from the perceivable being categorised visually, but is the means by which the perceivable is detected. The one exception here is the visual perception of light sources, which patterns like smell and hearing, where the perceivable light emanates from a source that may not be otherwise directly perceivable. Visual perception is both atypical and the primary modality through which humans categorise the perceivable, which gives unique status to the rôle of photons in human experience.[2]

Failure to make this distinction between the visible and the visual means of perceiving the visible has resulted in confusions like “colour (unlike other properties) exists only in the head of the observer”. Colour perception involves the detection and categorisation of difference (categorised by other means as light frequencies) reflecting off and refracting through the visible, and depends, inter alia, on the light frequencies emitted by the source and the molecular arrangement of the visible. 

Footnotes:

[1] A similar example in some species is the use of echo location, where the perceiver emits the radiation that reflects off surfaces in its vicinity.

[2] More of which later.

ChatGPT said:

Categorisation and the Modalities of Perception

Categorisation is a systematic interaction between:

1. The perceivable — that which can be detected and categorised;

2. The medium of detection — the physical means through which the perceivable becomes available to the senses (e.g. light for vision); and

3. The recognition system — the organism’s sensory and neural apparatus capable of detecting and categorising inputs through modalities such as vision, hearing, touch, smell, and taste.

This tripartite model holds clearly for some modalities and less distinctly for others. In the case of touch and taste, there is no mediating substance or signal between the perceivable and the receptor: the skin makes contact with the surface, the tongue with the chemical. Similarly, for smell and hearing, while there is no intermediary medium between stimulus and receptor — airborne molecules and compression waves respectively interact directly with the olfactory or auditory systems — these stimuli often emanate from sources that are not themselves directly perceivable. The same logic applies to echolocation in certain species, where emitted signals reflect off surfaces and return as perceptual data.

Vision, however, is structurally distinct. It introduces a mediating layer between the perceivable and the perceiver: photons. These photons are not the visible themselves, but the means by which the visible is detected. What is received by the visual system (light) is ontologically distinct from the object that emits or reflects it. This mediation is absent in other sensory modalities, making vision both atypical and, in humans, primary. One exception within vision is the perception of light sources themselves, which — like sound or smell — involves perceiving an emission rather than light reflected off another surface.

This layered structure has philosophical consequences. The failure to distinguish between the visible and the means of perceiving the visible has led to confusions, such as the claim that “colour (unlike other properties) exists only in the head of the observer.” Colour is not a free-floating quale but a categorisation of difference — specifically, differences in the frequencies of light reflected from and refracted through material surfaces, modulated by the properties of the light source and the molecular composition of what is seen.

---

Footnotes:

[1] Echolocation in species such as bats and dolphins offers an analogous structure: the perceiver emits the signal that reflects off nearby surfaces and returns as a perceptual input.

[2] The mediating role of photons in human experience — their ontological and epistemological status — will be addressed in more detail later.

9. Brain Function Is Organised By The Recognisable

The brain as recognition system is organised by the domains that it recognises. The domains that it recognises are both ouside and inside the body. The outside, which can include the meaningful expressions of others, is recognised via sensory sheets which detect external difference. The inside includes domains both outside and inside the brain. Outside the brain includes the musculo-skeletal system, which it detects via the peripheral nervous system, and homeostatic systems, to which it is connected via the limbic system. Inside the brain includes all the processes involved in recognising domains both inside the body but outside the brain and outside the body — an ability that varies across animal species. 

The recognition process, as the selection of variants by the domains being recognised, can be understood as the brain adapting to those domains: to the ecological context of the body (which includes the behaviours of other bodies), to the somatic context of the brain, and to the brain’s own recognition processes. Just as “Nature” selects genetic potential-for-development in the evolution of a species, “Nature” selects neurological potential-for-behaviour in the evolution of a neurological system embedded in the body of an organism in its lifetime.

ChatGPT said:

The Brain Organised by What It Recognises

The brain, as a recognition system, is organised by the domains it recognises. These domains include both what lies outside the body and what lies within it.

The external domains — which may include the meaningful expressions of others — are recognised through sensory sheets that detect difference beyond the body. The internal domains are both outside and inside the brain. Those outside the brain include the musculo-skeletal system, monitored via the peripheral nervous system, and homeostatic systems, connected through the limbic system. Those inside the brain include the brain’s own processes of recognition — which monitor both internal and external domains. The capacity to recognise such domains varies across species.

Recognition, on this model, is a selectional process: the domain being recognised selects some neural variants over others. In this sense, the brain adapts to the domains it recognises — to the ecological context of the body (including the behaviour of other bodies), to the somatic context of the brain, and to its own evolving processes of recognition.

Just as Nature selects genetic potential-for-development in biological evolution, Nature selects neurological potential-for-behaviour in the ontogeny of the brain: a recognition system embedded in a body, adapting in real time to the contexts in which it must function.

8. Categorising As Meaningful For An Organism

According to the TNGS, categorising occurs ‘on value’. That is, categorising neuronal systems are linked with value systems — cholinergic and aminergic — of the hedonic centres and limbic system, whose functions include homeostasis and appetites.[1] This means that categorising processes occur in the context of the current state of the organism, and the effect of this is to make categorising meaningful — to matter — to the categorising organism.

Footnote:

[1] Through this linkage, inherited value systems bias the categorising process in ways that have been of advantage to ancestors; the value systems of those who do not survive to reproduce are not passed down the generations of a biological lineage.

ChatGPT said:

Categorising "on Value"

According to Edelman's Theory of Neuronal Group Selection (TNGS), categorising occurs on value. That is, neuronal systems involved in categorisation are linked to value systems — notably the cholinergic and aminergic systems of the hedonic centres and limbic system, which regulate homeostasis, appetite, and emotion.[1] This linkage means that categorisation is not a neutral or detached process: it is modulated by the organism's current internal state. Categorising is embedded within the needs, drives, and affective orientations of the organism.

This has a profound consequence: categorising matters to the categorising organism. The act of categorising is not just informational — it is evaluative. It takes place in a context of significance, shaped by inherited predispositions and real-time physiological states. It is this affective embedding that makes categorisation meaningful in the experiential, not just informational, sense.

---

Footnote:

[1] Through this linkage, inherited value systems bias the categorising process in ways that have been advantageous to past generations. The value systems of organisms that failed to survive and reproduce are, by definition, not passed down the biological lineage.

11. Self-Reference

Semiotic systems are both a means of modelling of the categorisable and one domain within the modelling. A model of semiosis is part of modelling the categorisable semiotically. For example, a semiotic model of the categorisable may divide the categorisable into two distinct domains: the material and the semiotic.

ChatGPT said:

Semiotic Systems and the Categorisable

Semiotic systems are both a means of modelling the categorisable and a domain within what is being modelled. That is, a semiotic system can both model semiosis and be a participant in that modelling. To model the categorisable semiotically includes, reflexively, modelling the semiotic system itself.

For example, a semiotic model of the categorisable may distinguish between two domains: the material and the semiotic. In this case, the material is construed as that which is categorisable independent of semiosis, while the semiotic is construed as that which arises through the functioning of semiotic systems — as patterned potential for meaning.

Such a model is itself a semiotic categorisation. It is not a mirror of reality, but a way of construing experience as meaning.

10. No Images, Representations Or Symbols Inside Heads

On this model, there are no images in the brain (or mind[1]) — there are neuronal firing patterns. But some neuronal firing patterns correlate with differentiations of the visually perceivable. The firing of such patterns correlate with experiencing the differentiation of the visible, with having visual experiences.[2] Regenerations of past firing patterns can result in visual experiences in the absence of the originally experienced perceivable. By generating portions of different past visual experiences as an integrated whole, it is possible to create new visual experiences that have not previously been experienced — to imagine. And such simulations can be expressed through the skeleto-muscular system as pictorial images that others can experience. 

More generally, to be congruent[3], there are no symbols or representations (things) in brains[4]; there are cells and tissues and the functions they perform (processes). Neurological systems make symbols and representations possible, but, through skeleto-muscular action, as perceivable expressions which can be categorised and recategorised and re-expressed, and so on. Lamb (2005) has expressed this point clearly in modelling language with respect to neurological systems:

Likewise, if we consider production of speech, no one has ever found any evidence at all, neurological or otherwise, to support an hypothesis that it operates by the use of symbols represented somehow in the brain. The more realistic alternative is to suppose that what is internal is not symbolic representations of words or morphemes or the like, but the means of producing such forms (as speech or writing). 

Footnotes:

[1] Sometimes the word ‘mind’ is used in these contexts rather than ‘brain’. However, since the mind is not detectable as a (material) thing, it cannot be construed congruently as a place in the material universe that science models, and it is thus incongruent to speak of ‘in the mind’. See the discussion of ‘mind-as-process’ later in the chapter.

[2] See Edelman & Tononi (2000: 202-3).

[3] Those who might claim to speaking metaphorically (eg Hofstadter, Ramachandran) do not provide a congruent reformulation.

[4] The idea that symbols exist in brains is consistent with the instructionist model and with naïve realism: the belief that the world consists of true or real categories, and these are represented (accurately or not) in brains.

ChatGPT said:

No Images in the Brain

On this model, there are no images in the brain — nor in the mind.[1] There are neuronal firing patterns. Some of these patterns correlate with differentiations of the visually perceivable. Their firing correlates with experiencing such differentiations — that is, with having visual experiences.[2]

Reactivation of past patterns can produce visual experience in the absence of the originally perceived differentiables. When multiple such past patterns are selectively regenerated and integrated, new visual experiences may be constructed — imagined. These imagined experiences can be expressed through the skeleto-muscular system as pictorial images, which others can then perceive and categorise.

More generally: to remain congruent with this model, we must abandon the notion that there are symbols or representations in brains.[3] Brains contain cells and tissues, not things like words or pictures. What they do is perform functions. It is only through bodily expression — skeleto-muscular action — that symbols and representations become possible: as perceivable expressions that can be categorised, recategorised, and re-expressed.

Lamb (2005), modelling language in neurological terms, makes the point explicitly:

“Likewise, if we consider production of speech, no one has ever found any evidence at all, neurological or otherwise, to support an hypothesis that it operates by the use of symbols represented somehow in the brain. The more realistic alternative is to suppose that what is internal is not symbolic representations of words or morphemes or the like, but the means of producing such forms (as speech or writing).”

---

Footnotes:

[1] The term mind is often used in this context, but since the mind is not a detectable material entity, it cannot be congruently construed as a place within the material universe modelled by science. See the later discussion of mind-as-process.

[2] See Edelman & Tononi (2000: 202–3).

[3] Claims that this is merely metaphorical (e.g. Hofstadter, Ramachandran) fail to provide a congruent reformulation.

[4] The idea that symbols exist in brains aligns with both the instructionist model and with naïve realism — the belief that the world consists of real categories that are somehow mirrored inside the brain.

13. Meaning As A Process That Occurs In The Perceivable World

In modelling the categorisable, such as two domains: the material and the semiotic, semiosis is modelled as a process that goes on in the perceivable universe, in the same sense that galaxy formation and supernova explosions are processes that go on in the perceivable universe. Asking and answering the question ‘Why is there something instead of nothing?’ are processes that go on in the perceivable universe. Making meaning of the perceivable universe is something that organisms do, part of the universe recognising itself. Meaning is not of the categorisable domain of which meaning is made, nor does it transcend the domain of interactions (the perceivable universe) in which it occurs.

ChatGPT said:

Modelling Semiosis as a Process in the Universe

In modelling the categorisable — for example, by distinguishing domains such as the material and the semiotic — semiosis is itself modelled as a process occurring within the perceivable universe, in the same sense that galaxy formation or supernova explosions are processes occurring within the perceivable universe. Asking and answering the question “Why is there something rather than nothing?” are likewise processes within the universe — not external to it.

Meaning-making, then, is a process that organisms perform in the universe, not about it from outside. It is part of the universe recognising itself. Meaning does not belong to the domain of phenomena of which meaning is made, nor does it transcend the interactions through which it is constituted. It is immanent in the activity of semiosis: inseparable from the perceivable universe in which it arises and to which it refers.

12. To Refer To The Categorisable Is To Use Categorisations

To refer to the categorisable is to use specific categorisations of it, to express a specific model of it. For example, to refer to the perceivable as ‘the environment’ (or ‘context’ or ‘the perceivable’) is to categorise it within a larger model of meaning-making. Because of this, there is no “pre-theoretical” position that can be adopted on any subject, though some stances may be modelled as “pre-theoretical” for social-semiotic purposes. 

Further, no categorisables are ineffable[1], since any categorisable can be modelled and semiosis is modelling. However, some categorisables are modelled as being ineffable for social-semiotic purposes. 

Footnote:

[1] Cf Wittgenstein.

ChatGPT said:

To Categorise Is to Model

To refer to the categorisable is already to categorise it — that is, to use specific meaning-making resources to model it in particular ways. For instance, referring to the perceivable as “the environment”, “the context”, or “the perceivable” enacts different semiotic commitments, locating the referent within distinct systemic models. Each construal participates in a broader theoretical framing, whether or not that framing is made explicit.

There is therefore no position from which to speak that is “pre-theoretical,” though positions may be modelled as if they were pre-theoretical — for example, to project neutrality, naturalness, or inevitability — for social-semiotic effect.

By the same principle, no categorisables are ineffable, since to construe something as ineffable is itself a modelling move — a semiotic act. Semiosis is modelling. The ineffable is not that which cannot be modelled, but that which is modelled as that which resists or escapes modelling, often to mark symbolic boundaries of the sacred, the traumatic, or the sublime.

14. Models As Systems Of Relations

Bronowski[1]: 

Physics is not events, but observations; relativity is the understanding of the world, not as events, but as relations.

Smolin (1996: 289-90):

Indeed, for me the most important idea behind the developments of twentieth-century physics and cosmology is that things don’t have intrinsic properties at the fundamental level; all properties are about relations between things. This is the basic idea behind Einstein’s general theory of relativity, but it has a longer history; it goes back to at least to the seventeenth-century philosopher Leibniz, who opposed Newton’s ideas of space and time because Newton took space and time to exist absolutely, while Leibniz wanted to understand them as arising only as aspects of the relations among things. For me, this fight between those who want the world to be made out of absolute entities and those who want it to be made only out of relations is a key theme in the story of the development of modern physics. Moreover, I’m partial. I think Leibniz and the relationalists were right, and that what’s happening now in science can be understood as their triumph.

To model is to systematise categorisations, the valeur of each categorisation being defined by its relations to other categorisations. Individual categories are necessary but not sufficient: the function of each depends on the function of others, just as the function of a neuronal group depends on the functions of other neuronal groups, and the function of a gene depends on the functions of other genes. The process of categorising (analysis) distinguishes individual units, but these are not categorised without reference to what they differ from. Information is difference, in relation to other difference. 

Footnote:

[1] The Ascent Of Man episode 7: The Majestic Clockwork.

ChatGPT said:

Relational Modelling and the Systematics of Categorisation

Bronowski noted that physics is not a study of events, but of observations; that relativity is not a theory of things, but of relations. Smolin (1996: 289–90) develops this insight further, arguing that at the most fundamental level, things do not have intrinsic properties — all properties are relational. This principle, central to general relativity, finds antecedents in Leibniz’s opposition to Newton’s absolutist conception of space and time. Where Newton imagined space and time as entities in themselves, Leibniz understood them as emerging from the relations among things. Smolin identifies this as a defining tension in the history of physics: the contest between absolutists and relationalists — a contest in which he judges the relationalists to be, ultimately, victorious.

To model is to systematise categorisations — and the value (valeur) of any categorisation is given by its relations to other categorisations. Categorisations are defined differentially: no category is meaningful in isolation. Each derives its function from a network of contrasts, just as the function of a neuronal group depends on its interaction with other neuronal groups, and the function of a gene depends on its participation in a larger system of genetic expression.

The act of categorising — of analysing — isolates units, but such units are only identified in relation to what they are not. Information is difference — and only becomes information in relation to other difference.

15. Modelling Is Relating

Like all semiosis, modelling, including scientific modelling, involves relating categories of experience to each other with various degrees and scopes of consistency. Mathematical equations do this by relating measurements, including changing quantities, to each other. In formal systems, such as geometry, new unknown relations are reasoned from known relations, thereby expanding the system of relations by making the implicit explicit.

ChatGPT said:

Modelling as Relational Semiosis

Like all forms of semiosis, modelling — including scientific modelling — involves relating categories of experience to one another, establishing various degrees and scopes of consistency. In this context, mathematical equations serve as a means of relating measurements to each other, including the interrelation of changing quantities. In formal systems, such as geometry, new and previously unknown relations are deduced from established ones, thereby expanding the system of relations. This process makes the implicit explicit, uncovering previously hidden structures within the model.

17. Metafunctional Consistency In Meaning-Making

One aspect of “truth”[1] is consistency in meaning-making, and given the metafunctional dimensions of meaning-making, this entails metafunctional consistency in meaning-making: experiential, logical, interpersonal and textual.[2] To be ideationally consistent in meaning-making is to be consistent both in the representation of experience and in the logical relations said to obtain between representations of experience.[3] To be interpersonally consistent in meaning-making is to be consistent in the values given to — the stance taken on — ideational meanings. To be textually consistent in meaning-making is to be consistent in what is attended to as relevant with regard to ideational and interpersonal meanings.  Different consistencies — including tensions between construals of experience, values inherent in construals, and attentions paid to construals — creates diversity in modelling. 

Footnotes:

[1] The word ‘truth’ is a noun formed from the adjective ‘true’, which construes it metaphorically as an abstract thing in itself rather than congruently as a description of relations between things. 

[2] From interpersonal and textual perspectives, ideational distinctions are a means of elaborating what is valued and focussed upon. 

[3] The word ‘real’ is often used to mean ideationally true, but it is often also extended to mean that the specific categorisations of the description exist as properties of the perceivable, independent of the modelling framework.

ChatGPT revised:

Truth as Metafunctional Consistency

One aspect of what is conventionally called “truth”[1] is consistency in meaning-making. And since meaning-making operates along metafunctional dimensions, this entails metafunctional consistency: consistency across the experiential and logical (together forming the ideational), the interpersonal, and the textual.

To be ideationally consistent is to maintain coherence in the representation of experience and in the logical relations asserted between those representations.[2] This involves both internal consistency (e.g. maintaining consistent categorisations) and external consistency (e.g. aligning relations among representations with broader modelling frameworks).

To be interpersonally consistent is to adopt stances towards meanings — including attitudes, judgements, and value orientations — that are not erratic or self-contradictory across time and context. Here, consistency is not neutrality: it is the maintenance of a patterned evaluative orientation.

To be textually consistent is to attend selectively to ideational and interpersonal meanings in a way that is coherent and patterned: that is, to foreground and background meanings in ways that make sense within a perspective or model. This means attending to what is relevant, in a way that is itself relevant.

Modelling, then, is shaped not just by what is represented, but by how values are assigned and what is attended to. Diversity in modelling emerges not simply from different representations of experience, but from tensions between:
– experiential construals
– interpersonal valuations
– textual patterns of attention

These tensions — and the attempt to resolve or live within them — are what give modelling its creative range.

---

Footnotes

[1] The noun truth is derived from the adjective true, abstracting it into an object-like entity — a metaphoric construal. Congruently, true functions to describe a relation among things, rather than as a “thing” in itself.

[2] From the interpersonal and textual perspectives, ideational meanings are not primary but functional: they are the means by which what is valued and what is attended to are elaborated.

[3] The term real is often used to mean ideationally true, but it is also commonly extended to imply that the specific categorisations involved correspond to properties of the perceivable, independent of the modelling framework — an extrapolation that conflates modelling with ontology.

16. The Metafunctional Dimensions Of Modelling Semiotically

The conditions of modelling the categorisable semiotically can be understood in terms of the metafunctional dimensions of meaning-making: the ideational, which includes the experiential and the logical, the interpersonal and the textual. 

Firstly, models are located in the space of ideational variation. Models are organised through experiencing the categorisable.[1] Categorisable difference selects the categories that may or may not be organised into a model of the categorisable. So models depend on the recognition functionality of the neurological system and the prosthetic technologies that extend its recognition abilities, and they depend on the specific experience trajectories of modellers. 

Secondly, models are located in the space of interpersonal variation. Models are organised by values that bias the orientation of modellers to different categories of experience. Limbic system functions that have been of adaptive value to ancestors invest the categories (that are selected by categorisable difference) with positive or negative value, and the complexification of categories within individuals — through the categorisation of categories and their differentiation through semiotic interactions with others — is the complexification of categorial values. Models are motivated organisations of categorisations. 

Thirdly, models are located in the space of textual variation. Models are organised through selective attention to value-categories: focusing on some categories as relevant, and filtering out others as irrelevant.[2] Some value-categories are prominent threads in the weaving together of meanings, while others are thin or absent. Because modelling occurs through a perspectival lens, it is both enabling and disabling: a model is conditional on the assumptions on which it is organised.[3] Models are ‘ways of seeing’ (Berger 1972). 

Footnotes:

[1] The ‘categorisable’ includes categorisations of the categorisable, categorisations of categorisations of the categorisable, and so on.

[2] This relates to Pike’s notion that a theory is like a window that only faces in one direction. 

[3] The influence of ones perspectival lens on categorising was shown by a seminal psychology experiment by Rosenhan (reported in Slater 2004) in which subjects faking their way into mental institutions were not detected by most psychiatrists.

ChatGPT revised:

The Metafunctional Conditions of Modelling

The conditions under which we model the categorisable semiotically can be understood through the metafunctional dimensions of meaning-making: the ideational, encompassing the experiential and the logical; the interpersonal; and the textual.

1. Ideational variation: organising experience
Models are located in the space of ideational variation: they are organised through the experience of the categorisable.[1] It is difference in the categorisable that selects the categories through which it may be modelled. This means that models depend on the recognition functionality of the neurological system, including prosthetic technologies that extend its perceptual reach, and on the particular experiential trajectories of individual modellers.

2. Interpersonal variation: organising value
Models are also located in the space of interpersonal variation: they are organised by the value systems that orient the modeller towards particular kinds of experience. The limbic system — shaped by evolutionary pressures on ancestral bodies — biases the modeller towards or away from particular categories by investing them with positive or negative value. As categories become more complex, both through internal differentiation and through semiotic interaction with others, so too do the values attached to them. Models are not neutral systems of classification; they are motivated organisations of categorisation.

3. Textual variation: organising relevance
Finally, models are located in the space of textual variation: they are organised through selective attention to value-laden categories. This includes foregrounding some categories as salient while filtering out others as irrelevant.[2] Some become prominent organising threads in a fabric of meaning, while others remain peripheral or are omitted entirely. Every model, in this sense, is perspectival: it is a way of seeing (Berger 1972), and like all perspectives, it both reveals and obscures. A model is structured by the assumptions it inherits and enacts — its exclusions are as consequential as its inclusions.[3]

---

Footnotes

[1] The ‘categorisable’ includes not only directly experienced phenomena, but also categorisations of the categorisable, and categorisations of those categorisations, recursively.
[2] Pike famously observed that a theory is like a window that only faces one way.
[3] The influence of perspectival framing on categorisation was illustrated by Rosenhan’s experiment (reported in Slater 2004), in which actors feigned psychiatric symptoms to gain admission to mental institutions and were largely undetected once inside — demonstrating the self-reinforcing bias of diagnostic frames.

18. ‘Consistency’ Means ‘Mutual Fit’

Consistent meaning-making is meaning-making that fits in the context of other meaning-making. Metafunctionally, this is experiential meaning-making fitting in the context of other experiential meaning-making: construals of experience fitting other construals of experience; logical meaning-making fitting in the context of other logical meaning-making: logical relations (between construals of experience) fitting other logical relations (between construals of experience); interpersonal meaning-making fitting in the context of other interpersonal meaning-making: valuings (of construals of experience) fitting other valuings (of construals of experience); textual meaning-making fitting in the context of other textual meaning-making: saliences (of valuings and construals of experience) fitting other saliences (of valuings and construals of experience).

ChatGPT revised:

Consistency as Contextual Fit in Meaning-Making

Consistent meaning-making is meaning-making that fits — that coheres within the context of other meaning-making. Each metafunctional dimension brings its own type of fit, its own kind of consistency:

• Experiential consistency is about construals of experience fitting with other construals of experience. It concerns whether the ways experience is represented hold together across time and context.

• Logical consistency is about logical relations among construals of experience fitting with other logical relations. It concerns the systematicity of reasoning: how well inferential or implicational links hold across a network of meanings.

• Interpersonal consistency is about evaluative stances — valuings of construals of experience — fitting with other such valuings. It concerns the coherence of attitudes and judgements over time, across contexts and interlocutors.

• Textual consistency is about patterns of salience — what is made prominent or backgrounded — fitting with other such patterns. It concerns the coherence of attentional framing: how relevance is construed across texts or episodes of semiosis.

Each dimension of meaning-making provides a context for interpreting the others. Consistency is not about mechanical repetition, but about meaningful alignment — about how each act of semiosis harmonises with the broader symphony of meaning in which it participates.

19. The Variable Scope Of Semiotic Consistency

Consistency is a gradable property, varying from as low a value as ‘not being inconsistent’ to ‘being in harmony’ to as high a value as ‘being wholly consistent’, and models may vary in terms of consistency within some domain of categorising. The “truth” of a model depends on the degree to which it fits other models. The scope within which meanings may be consistent varies from the very local to the more global. For example, ideational construals may be consistent within or across[1] fields, within or across tenors, within or across modes. Interpersonal values may be consistent within or across fields, within or across tenors, within or across modes. Textual saliences may be consistent within or across fields, within or across tenors, within or across modes.

Footnote:

[1] This book is an attempt to establish some degree of ideational consistency across fields.

ChatGPT revised:

Degrees and Domains of Consistency

Consistency is a gradable property. It can range from the minimal — simply not being inconsistent — to being in harmony, all the way to being wholly consistent. Models may vary in their degree of internal consistency and in how well they fit with other models within a given domain of categorisation.

The “truth” of a model lies in the degree to which it fits other models — not as an absolute state, but as a matter of alignment across systems of meaning. This fit is always scoped: the scope of consistency may be narrow and local, or broad and global.

For instance:

• Ideational construals may be consistent within or across fields of knowledge, tenors of interaction, or modes of expression.

• Interpersonal values may be consistent within or across these same dimensions — fields, tenors, and modes.

• Textual saliences — what is foregrounded or backgrounded — may likewise be consistent within or across fields, tenors, and modes.

Each of these axes offers a different plane along which consistency (and inconsistency) can be tracked and evaluated.

This book is, in part, an attempt to establish some degree of ideational consistency across fields.

21. Aligning With Specific Metafunctional Consistencies

Meaning potential thus involves a web of different networks of metafunctional consistencies: different construals, different values, different foci of attention. Meaning-makers variously align (consistently or inconsistently[1]) with different networks of consistency within the overall web of variant consistencies. Those who share a specific network of consistency potentially form a community of ‘like-minded’ individuals with a ‘common interest’: a community formed around a way of construing experience, a community formed around a way of valuing a construal, a community formed around a way of grading the relative importance of construals and values.[2] Since each individual can align (consistently or inconsistently) with multiple networks, each can belong to multiple communities, “us”, and disassociate from multiple communities, “you” or “them”.

Footnotes:

[1] There is, of course, the question of consistency between what is said (semiotic behaviour) and what is done (non-semiotic behaviour). 

[2] If each variant consistency is located along three dimensions: the ideational, interpersonal and textual, individuals that align with specific consistencies can be located at different points in the metafunctional space defined by those dimensions; communities correspond to clusters in that space.

ChatGPT revised:

Meaning Potential and Networks of Consistency

Meaning potential consists of a web of variant networks of metafunctional consistency — networks of different construals, different valuings, and different focalisations of attention. Meaning-makers align (to varying degrees of consistency or inconsistency¹) with these networks, which together form the semiotic landscape of possible meaning.

Those who share alignment with a particular network of consistency form a potential community of like-minded individuals: individuals who share a common interest — a way of construing experience, a way of valuing those construals, a way of assigning salience among them.² These communities are not fixed but contingent formations within the web of variation.

Because each individual may align — consistently or inconsistently — with multiple such networks, each may simultaneously belong to multiple ‘us’ communities and disaffiliate from multiple ‘you’ or ‘them’ communities. The web of meaning potential is not a stable map of identity but a shifting topology of alignment and disalignment across metafunctional dimensions.