Emergent Causality and the Foundation of Consciousness

Bennett, Michael Timothy

doi:10.1007/978-3-031-33469-6_6

Cited by 6 publications

(26 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The distinction between software and hardware, though useful, is unsuitable for reasoning about cause [15]. A software agent in an interactive setting performs subjectively, relying on hardware through which it is interpreted [14].…”

Section: Arguments and Resultsmentioning

confidence: 99%

“…We must ascertain what is objective rather than subjective, and so we must begin at the level of the environment rather than the agent. To this end, previous work [18,17,15,19] proposed a "de facto" pancomputational [20] model of all possible environments and aspects thereof, including all abstractions and goal directed behaviours, which we refine and extend. While the formalism we present here is a departure from past work, it is equivalent with respect to those previously published proofs which we reference [17].…”

Section: Arguments and Resultsmentioning

confidence: 99%

“…Maximising policy "weakness" was proven necessary and sufficient to maximise sample efficiency [17, prop. 1, 2] and identify cause [15]. In experiments, weak policies outperformed simple by 110 − 500%.…”

Section: Key Questionsmentioning

confidence: 99%

“…: As it is used in AGI research [10], complexity is intended to help us infer the program which generated or caused data. If one can identify that which caused past data, then one can "generalise" to predict the outcomes in future interactions, to maximise performance [15]. We are concerned with adaptation or "the ability to generalise" [16], not any specific circumstance.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Is Complexity an Illusion?

Bennett

2024

Preprint

View full text Add to dashboard Cite

Simplicity is held by many to be the key to general intelligence. Simpler models tend to “generalise”, identifying the cause or generator of data with greater sample efficiency. The implications of the correlation between simplicity and generalisation extend far beyond computer science, addressing questions of physics and even biology. Yet simplicity is a property of form, while generalisation is of function. In interactive settings, any correlation between the two depends on interpretation. In theory there could be no correlation and yet in practice, there is. Previous theoretical work showed generalisation to be a consequence of “weak” constraints implied by function, not form. Experiments demonstrated choosing weak constraints over simple forms yielded a 110 − 500% improvement in generalisation rate. Here we show that if one does not presuppose an abstraction layer, then all forms have equal complexity. However, in the context of a spatially and temporally extended abstraction layer, efficiency demands weak constraints take simple forms, and simplicity becomes correlated with generalisation. Simplicity has no causal influence on generalisation, but appears to due to confounding.

show abstract

Section: Arguments and Resultsmentioning

confidence: 99%

Section: Arguments and Resultsmentioning

confidence: 99%

Section: Key Questionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Is Complexity an Illusion?

Bennett

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Informed by recent results from machine learning [11][12][13], we hold that the environment learns organisms that exhibit fit behaviour, via the algorithm of natural selection.…”

Section: The Psychophysical Principle Of Causalitymentioning

confidence: 97%

The Phenomenal Is Functional: A Unified Theory of Consciousness and Computation

Bennett,

Welsh

2023

Preprint

View full text Add to dashboard Cite

Please note this is a draft on which we are seeking feedback. Substantial changes and a third author are likely be added to the next version. The hard problem of consciousness asks why there is something it is like to be a conscious organism. We address this from 1st principles, by constructing a formalism that unifies lower and higher order theories of consciousness. We assume pancomputationalism and hold that the environment learns organisms that exhibit fit behaviour via the algorithm we call natural selection. Selection learns organisms that learn to classify causes, facilitating adaptation. Recent experimental and mathematical computer science elucidates how. Scaling this capacity implies a progressively higher order of ``causal identity'' facilitating reafference and P-consciousness, then self awareness and A-consciousness, and then meta self awareness. We then use this to resolve the hard problem in precise terms. First, we deny that a philosophical zombie is in all circumstances as capable as a P-conscious being. This is because a variable presupposes an object to which a value is assigned. Whether X causes Y depends on the choice of X, so causality is learned by learning X such that X causes Y, not by presupposing X and then learning if X causes Y (presupposing rather than inferring abstractions can reduce sample efficiency in learning). However, learning is a discriminatory process that requires states be differentiated by value. Without objects, variables or values, there is only quality. By this we mean an organism is attracted to or repulsed by a physical state. Learning reduces quality into objects by constructing policies classifying cause of affect (``representations'' are just behaviour triggered by phenomenal content). Where selection pressures require an organism classify its own interventions, that policy (a ``1st order causal identity'') has a quality that persists across interventions, and so there is something it is like to be that organism. Thus organisms have P-consciousness because it allows them to adapt with greater sample efficiency, and infer the cause of affect. We then argue neither P nor A-consciousness alone are remarkable, but when P-consciousness gives rise to A-consciousness we obtain ``H-consciousness'' (what Boltuc argues is the crux of the hard problem). This occurs when selection pressures require organism o infer organism u's prediction of o's interventions a ``2nd order causal identity'' approximating intent). A-consciousness is the contents of 2nd order causal identities, and by predicting another's prediction of one's own 1st order causal identities it becomes possible to know what one knows and feels, and act upon this information to communicate meaning in the Gricean sense. Thus P and A-consciousness are two aspects of H-concsiousness, the process of learning and acting in accord with a hierarchy of causal identities that simplify the environment into classifiers of cause and affect. We call this the psychophysical principle of causality.

show abstract

Is Complexity an Illusion?

Bennett

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Emergent Causality and the Foundation of Consciousness

Cited by 6 publications

References 14 publications

Is Complexity an Illusion?

Is Complexity an Illusion?

The Phenomenal Is Functional: A Unified Theory of Consciousness and Computation

Is Complexity an Illusion?

Contact Info

Product

Resources

About