Formalizing Falsification for Theories of Consciousness Across Computational Hierarchies

• URL: http://arxiv.org/abs/2006.07390v2
• Date: Sat, 5 Sep 2020 16:31:31 GMT
• Title: Formalizing Falsification for Theories of Consciousness Across Computational Hierarchies
• Authors: Jake R. Hanson and Sara I. Walker
• Abstract summary: Integrated Information Theory (IIT) is widely regarded as the preeminent theory of consciousness. Epistemological issues in the form of the "unfolding argument" have provided a refutation of IIT. We show how IIT is simultaneously falsified at the finite-state automaton level and unfalsifiable at the state automaton level.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The scientific study of consciousness is currently undergoing a critical transition in the form of a rapidly evolving scientific debate regarding whether or not currently proposed theories can be assessed for their scientific validity. At the forefront of this debate is Integrated Information Theory (IIT), widely regarded as the preeminent theory of consciousness because of its quantification of consciousness in terms a scalar mathematical measure called $\Phi$ that is, in principle, measurable. Epistemological issues in the form of the "unfolding argument" have provided a refutation of IIT by demonstrating how it permits functionally identical systems to have differences in their predicted consciousness. The implication is that IIT and any other proposed theory based on a system's causal structure may already be falsified even in the absence of experimental refutation. However, so far the arguments surrounding the issue of falsification of theories of consciousness are too abstract to readily determine the scope of their validity. Here, we make these abstract arguments concrete by providing a simple example of functionally equivalent machines realizable with table-top electronics that take the form of isomorphic digital circuits with and without feedback. This allows us to explicitly demonstrate the different levels of abstraction at which a theory of consciousness can be assessed. Within this computational hierarchy, we show how IIT is simultaneously falsified at the finite-state automaton (FSA) level and unfalsifiable at the combinatorial state automaton (CSA) level. We use this example to illustrate a more general set of criteria for theories of consciousness: to avoid being unfalsifiable or already falsified scientific theories of consciousness must be invariant with respect to changes that leave the inference procedure fixed at a given level in a computational hierarchy.

Related papers

• Learning Discrete Concepts in Latent Hierarchical Models [73.01229236386148]
  Learning concepts from natural high-dimensional data holds potential in building human-aligned and interpretable machine learning models. We formalize concepts as discrete latent causal variables that are related via a hierarchical causal model. We substantiate our theoretical claims with synthetic data experiments.
  arXiv  Detail & Related papers  (2024-06-01T18:01:03Z)
• Artificial consciousness. Some logical and conceptual preliminaries [0.0]
  We argue for the necessity of using dimensions and profiles of consciousness for a balanced discussion about their possible instantiation or realisation in artificial systems. Our primary goal in this paper is to review the main theoretical questions that arise in the domain of artificial consciousness.
  arXiv  Detail & Related papers  (2024-03-29T13:47:47Z)
• Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales [54.78115855552886]
  We show how to construct over-complete invariants with a Convolutional Neural Networks (CNN)-like hierarchical architecture. With the over-completeness, discriminative features w.r.t. the task can be adaptively formed in a Neural Architecture Search (NAS)-like manner. For robust and interpretable vision tasks at larger scales, hierarchical invariant representation can be considered as an effective alternative to traditional CNN and invariants.
  arXiv  Detail & Related papers  (2024-02-23T16:50:07Z)
• A Theory of Unsupervised Speech Recognition [60.12287608968879]
  Unsupervised speech recognition (ASR-U) is the problem of learning automatic speech recognition systems from unpaired speech-only and text-only corpora. We propose a general theoretical framework to study the properties of ASR-U systems based on random matrix theory and the theory of neural tangent kernels.
  arXiv  Detail & Related papers  (2023-06-09T08:12:27Z)
• Measuring the integrated information of a quantum mechanism [0.0]
  Integrated information theory was originally conceived as a theory of consciousness. It remains to be determined whether IIT as a theory of consciousness is compatible with quantum mechanics as a theory of microphysics.
  arXiv  Detail & Related papers  (2023-01-04T22:27:36Z)
• Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization [49.00409552570441]
  We study the role of conceptualization in commonsense reasoning, and formulate a framework to replicate human conceptual induction. We apply the framework to ATOMIC, a large-scale human-annotated CKG, aided by the taxonomy Probase.
  arXiv  Detail & Related papers  (2022-06-03T12:24:49Z)
• Quantum realism: axiomatization and quantification [77.34726150561087]
  We build an axiomatization for quantum realism -- a notion of realism compatible with quantum theory. We explicitly construct some classes of entropic quantifiers that are shown to satisfy almost all of the proposed axioms.
  arXiv  Detail & Related papers  (2021-10-10T18:08:42Z)
• A Mathematical Walkthrough and Discussion of the Free Energy Principle [0.0]
  The Free-Energy-Principle (FEP) is an influential and controversial theory which postulates a connection between the thermodynamics of self-organization and learning through variational inference. FEP has been applied extensively in neuroscience, and is beginning to make inroads in machine learning by spurring the construction of novel and powerful algorithms by which action, perception, and learning can all be unified under a single objective. Here, we aim to provide a mathematically detailed, yet intuitive walk-through of the formulation and central claims of the FEP while also providing a discussion of the assumptions necessary and potential limitations of the theory.
  arXiv  Detail & Related papers  (2021-08-30T16:11:49Z)
• Resource theory of imaginarity: Quantification and state conversion [48.7576911714538]
  Resource theory of imaginarity has been introduced, allowing for a systematic study of complex numbers in quantum mechanics and quantum information theory. We investigate imaginarity quantification, focusing on the geometric imaginarity and the robustness of imaginarity, and apply these tools to the state conversion problem in imaginarity theory. Our study reveals the significance of complex numbers in quantum physics, and proves that imaginarity is a resource in optical experiments.
  arXiv  Detail & Related papers  (2021-03-02T15:30:27Z)
• No Substitute for Functionalism -- A Reply to 'Falsification & Consciousness' [0.0]
  This reply identifies avenues of expansion for the model proposed in [1], allowing us to distinguish between different types of variation. Motivated by examples from neural networks, state machines and Turing machines, we will prove that substitutions do not exist for a very broad class of Level-1 functionalist theories.
  arXiv  Detail & Related papers  (2020-05-28T08:12:07Z)
• A Non-equilibrium Thermodynamic Framework of Consciousness [0.0]
  We use functionalist and causal structure theories to motivate a new non-equilibrium thermodynamic framework of consciousness. The main hypothesis in this paper will be two thermodynamic conditions that a system will have to satisfy in order to be 'conscious'
  arXiv  Detail & Related papers  (2020-05-04T20:01:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.