A theory of consciousness from a theoretical computer science perspective: Insights from the Conscious Turing Machine

Evaluating the explanatory power of the Conscious Turing Machine

The recent "Conscious Turing Machine" (CTM) proposal offered by Manuel and Lenore Blum aims to define and explore consciousness, contribute to the solution of the hard problem, and demonstrate the value of theoretical computer science with respect to the study of consciousness. Surprisingly, given the ambitiousness and novelty of the proposal (and the prominence of its creators), CTM has received relatively little attention. We here seek to remedy this by offering an exhaustive evaluation of CTM. Our evaluation considers the explanatory power of CTM in three different domains of interdisciplinary consciousness studies: the philosophy of mind, cognitive neuroscience, and computation. Based on our evaluation in each of the target domains, at present, any claim that CTM constitutes progress is premature. Nevertheless, the model has potential, and we highlight several possible avenues of future research which proponents of the model may pursue in its development.

Eight challenges in developing theory of intelligence

A good theory of mathematical beauty is more practical than any current observation, as new predictions about physical reality can be self-consistently verified. This belief applies to the current status of understanding deep neural networks including large language models and even the biological intelligence. Toy models provide a metaphor of physical reality, allowing mathematically formulating the reality (i.e., the so-called theory), which can be updated as more conjectures are justified or refuted. One does not need to present all details in a model, but rather, more abstract models are constructed, as complex systems such as the brains or deep networks have many sloppy dimensions but much less stiff dimensions that strongly impact macroscopic observables. This type of bottom-up mechanistic modeling is still promising in the modern era of understanding the natural or artificial intelligence. Here, we shed light on eight challenges in developing theory of intelligence following this theoretical paradigm. Theses challenges are representation learning, generalization, adversarial robustness, continual learning, causal learning, internal model of the brain, next-token prediction, and the mechanics of subjective experience.

Design and evaluation of a global workspace agent embodied in a realistic multimodal environment

As the apparent intelligence of artificial neural networks (ANNs) advances, they are increasingly likened to the functional networks and information processing capabilities of the human brain. Such comparisons have typically focused on particular modalities, such as vision or language. The next frontier is to use the latest advances in ANNs to design and investigate scalable models of higher-level cognitive processes, such as conscious information access, which have historically lacked concrete and specific hypotheses for scientific evaluation. In this work, we propose and then empirically assess an embodied agent with a structure based on global workspace theory (GWT) as specified in the recently proposed "indicator properties" of consciousness. In contrast to prior works on GWT which utilized single modalities, our agent is trained to navigate 3D environments based on realistic audiovisual inputs. We find that the global workspace architecture performs better and more robustly at smaller working memory sizes, as compared to a standard recurrent architecture. Beyond performance, we perform a series of analyses on the learned representations of our architecture and share findings that point to task complexity and regularization being essential for feature learning and the development of meaningful attentional patterns within the workspace.

Toward a universal theory of consciousness

While falsifiability has been broadly discussed as a desirable property of a theory of consciousness, in this paper, we introduce the meta-theoretic concept of "Universality" as an additional desirable property for a theory of consciousness. The concept of universality, often assumed in physics, posits that the fundamental laws of nature are consistent and apply equally everywhere in the universe and remain constant over time. This assumption is crucial in science, acting as a guiding principle for developing and testing theories. When applied to theories of consciousness, universality can be defined as the ability of a theory to determine whether any fully described dynamical system is conscious or non-conscious. Importantly, for a theory to be universal, the determinant of consciousness needs to be defined as an intrinsic property of a system as opposed to replying on the interpretation of the external observer. The importance of universality originates from the consideration that given that consciousness is a natural phenomenon, it could in principle manifest in any physical system that satisfies a certain set of conditions whether it is biological or non-biological. To date, apart from a few exceptions, most existing theories do not possess this property. Instead, they tend to make predictions as to the neural correlates of consciousness based on the interpretations of brain functions, which makes those theories only applicable to brain-centric systems. While current functionalist theories of consciousness tend to be heavily reliant on our interpretations of brain functions, we argue that functionalist theories could be converted to a universal theory by specifying mathematical formulations of the constituent concepts. While neurobiological and functionalist theories retain their utility in practice, we will eventually need a universal theory to fully explain why certain types of systems possess consciousness.

Towards a structural turn in consciousness science

Recent activities in virtually all fields engaged in consciousness studies indicate early signs of a structural turn, where verbal descriptions or simple formalisations of conscious experiences are replaced by structural tools, most notably mathematical spaces. My goal here is to offer three comments that, in my opinion, are essential to avoid misunderstandings in these developments early on. These comments concern metaphysical premises of structural approaches, the viability of structure-preserving mappings, and the question of what a structure of conscious experience is in the first place. I will also explain what, in my opinion, are the great promises of structural methodologies and how they might impact consciousness science at large.

Multilevel development of cognitive abilities in an artificial neural network

Several neuronal mechanisms have been proposed to account for the formation of cognitive abilities through postnatal interactions with the physical and sociocultural environment. Here, we introduce a three-level computational model of information processing and acquisition of cognitive abilities. We propose minimal architectural requirements to build these levels, and how the parameters affect their performance and relationships. The first sensorimotor level handles local nonconscious processing, here during a visual classification task. The second level or cognitive level globally integrates the information from multiple local processors via long-ranged connections and synthesizes it in a global, but still nonconscious, manner. The third and cognitively highest level handles the information globally and consciously. It is based on the global neuronal workspace (GNW) theory and is referred to as the conscious level. We use the trace and delay conditioning tasks to, respectively, challenge the second and third levels. Results first highlight the necessity of epigenesis through the selection and stabilization of synapses at both local and global scales to allow the network to solve the first two tasks. At the global scale, dopamine appears necessary to properly provide credit assignment despite the temporal delay between perception and reward. At the third level, the presence of interneurons becomes necessary to maintain a self-sustained representation within the GNW in the absence of sensory input. Finally, while balanced spontaneous intrinsic activity facilitates epigenesis at both local and global scales, the balanced excitatory/inhibitory ratio increases performance. We discuss the plausibility of the model in both neurodevelopmental and artificial intelligence terms.

A theory of consciousness from a theoretical computer science perspective: Insights from the Conscious Turing Machine

This paper examines consciousness from the perspective of theoretical computer science (TCS), a branch of mathematics concerned with understanding the underlying principles of computation and complexity, including the implications and surprising consequences of resource limitations. We propose a formal TCS model, the Conscious Turing Machine (CTM). The CTM is influenced by Alan Turing's simple yet powerful model of computation, the Turing machine (TM), and by the global workspace theory (GWT) of consciousness originated by cognitive neuroscientist Bernard Baars and further developed by him, Stanislas Dehaene, Jean-Pierre Changeux, George Mashour, and others. Phenomena generally associated with consciousness, such as blindsight, inattentional blindness, change blindness, dream creation, and free will, are considered. Explanations derived from the model draw confirmation from consistencies at a high level, well above the level of neurons, with the cognitive neuroscience literature.