Artificial Intelligence and the Common Sense of Animals

Disentangled representations for causal cognition

Complex adaptive agents consistently achieve their goals by solving problems that seem to require an understanding of causal information, information pertaining to the causal relationships that exist among elements of combined agent-environment systems. Causal cognition studies and describes the main characteristics of causal learning and reasoning in human and non-human animals, offering a conceptual framework to discuss cognitive performances based on the level of apparent causal understanding of a task. Despite the use of formal intervention-based models of causality, including causal Bayesian networks, psychological and behavioural research on causal cognition does not yet offer a computational account that operationalises how agents acquire a causal understanding of the world seemingly from scratch, i.e. without a-priori knowledge of relevant features of the environment. Research on causality in machine and reinforcement learning, especially involving disentanglement as a candidate process to build causal representations, represents on the other hand a concrete attempt at designing artificial agents that can learn about causality, shedding light on the inner workings of natural causal cognition. In this work, we connect these two areas of research to build a unifying framework for causal cognition that will offer a computational perspective on studies of animal cognition, and provide insights in the development of new algorithms for causal reinforcement learning in AI.

Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks

Striking progress has been made in understanding cognition by analyzing how the brain is engaged in different modes of information processing. For instance, so-called synergistic information (information encoded by a set of neurons but not by any subset) plays a key role in areas of the human brain linked with complex cognition. However, two questions remain unanswered: (a) how and why a cognitive system can become highly synergistic; and (b) how informational states map onto artificial neural networks in various learning modes. Here we employ an information-decomposition framework to investigate neural networks performing cognitive tasks. Our results show that synergy increases as networks learn multiple diverse tasks, and that in tasks requiring integration of multiple sources, performance critically relies on synergistic neurons. Overall, our results suggest that synergy is used to combine information from multiple modalities-and more generally for flexible and efficient learning. These findings reveal new ways of investigating how and why learning systems employ specific information-processing strategies, and support the principle that the capacity for general-purpose learning critically relies on the system's information dynamics.

Artificial intelligence: revolutionizing cardiology with large language models

Natural language processing techniques are having an increasing impact on clinical care from patient, clinician, administrator, and research perspective. Among others are automated generation of clinical notes and discharge letters, medical term coding for billing, medical chatbots both for patients and clinicians, data enrichment in the identification of disease symptoms or diagnosis, cohort selection for clinical trial, and auditing purposes. In the review, an overview of the history in natural language processing techniques developed with brief technical background is presented. Subsequently, the review will discuss implementation strategies of natural language processing tools, thereby specifically focusing on large language models, and conclude with future opportunities in the application of such techniques in the field of cardiology.

Information Optimization and Transferable State Abstractions in Deep Reinforcement Learning

While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a time. As a result, the information they acquire is hardly reusable in new situations. Here, we introduce a new perspective on the problem of leveraging prior knowledge to solve future tasks. We show that learning discrete representations of sensory inputs can provide a high-level abstraction that is common across multiple tasks, thus facilitating the transference of information. In particular, we show that it is possible to learn such representations by self-supervision, following an information theoretic approach. Our method is able to learn abstractions in locomotive and optimal control tasks that increase the sample efficiency in both known and unknown tasks, opening a new path to endow artificial agents with generalization abilities.

Congratulations to Animal Cognition on its 50th birthday! Some thoughts on the last 50 years of animal cognition research

In this article, the author reflects on some of the key issues that have arisen in comparative cognition and the role and impact of the journal Animal Cognition through its first 25 years by pretending to look back at this period from the year 2047. Successes within comparative cognition are described and the role that Animal Cognition has played in the growth of comparative cognition are discussed. Concerns are presented about issues that affect the opportunities that researchers have to work with nonhuman species and to produce good comparative cognitive science. Prescriptions for what the author hopes will happen next also are offered all in the lens of a prospectively imagined retrospective on this field.

The signature-testing approach to mapping biological and artificial intelligences

Making inferences from behaviour to cognition is problematic due to a many-to-one mapping problem, in which any one behaviour can be generated by multiple possible cognitive processes. Attempts to cross this inferential gap when comparing human intelligence to that of animals or machines can generate great debate. Here, we discuss the challenges of making comparisons using 'success-testing' approaches and call attention to an alternate experimental framework, the 'signature-testing' approach. Signature testing places the search for information-processing errors, biases, and other patterns centre stage, rather than focussing predominantly on problem-solving success. We highlight current research on both biological and artificial intelligence that fits within this framework and is creating proactive research programs that make strong inferences about the similarities and differences between the content of human, animal, and machine minds.

Direct Human-AI Comparison in the Animal-AI Environment

Artificial Intelligence is making rapid and remarkable progress in the development of more sophisticated and powerful systems. However, the acknowledgement of several problems with modern machine learning approaches has prompted a shift in AI benchmarking away from task-oriented testing (such as Chess and Go) towards ability-oriented testing, in which AI systems are tested on their capacity to solve certain kinds of novel problems. The Animal-AI Environment is one such benchmark which aims to apply the ability-oriented testing used in comparative psychology to AI systems. Here, we present the first direct human-AI comparison in the Animal-AI Environment, using children aged 6-10 (n = 52). We found that children of all ages were significantly better than a sample of 30 AIs across most of the tests we examined, as well as performing significantly better than the two top-scoring AIs, "ironbar" and "Trrrrr," from the Animal-AI Olympics Competition 2019. While children and AIs performed similarly on basic navigational tasks, AIs performed significantly worse in more complex cognitive tests, including detour tasks, spatial elimination tasks, and object permanence tasks, indicating that AIs lack several cognitive abilities that children aged 6-10 possess. Both children and AIs performed poorly on tool-use tasks, suggesting that these tests are challenging for both biological and non-biological machines.

Deep Reinforcement Learning Based Trajectory Planning Under Uncertain Constraints

With the advance in algorithms, deep reinforcement learning (DRL) offers solutions to trajectory planning under uncertain environments. Different from traditional trajectory planning which requires lots of effort to tackle complicated high-dimensional problems, the recently proposed DRL enables the robot manipulator to autonomously learn and discover optimal trajectory planning by interacting with the environment. In this article, we present state-of-the-art DRL-based collision-avoidance trajectory planning for uncertain environments such as a safe human coexistent environment. Since the robot manipulator operates in high dimensional continuous state-action spaces, model-free, policy gradient-based soft actor-critic (SAC), and deep deterministic policy gradient (DDPG) framework are adapted to our scenario for comparison. In order to assess our proposal, we simulate a 7-DOF Panda (Franka Emika) robot manipulator in the PyBullet physics engine and then evaluate its trajectory planning with reward, loss, safe rate, and accuracy. Finally, our final report shows the effectiveness of state-of-the-art DRL algorithms for trajectory planning under uncertain environments with zero collision after 5,000 episodes of training.

General intelligence disentangled via a generality metric for natural and artificial intelligence

Success in all sorts of situations is the most classical interpretation of general intelligence. Under limited resources, however, the capability of an agent must necessarily be limited too, and generality needs to be understood as comprehensive performance up to a level of difficulty. The degree of generality then refers to the way an agent's capability is distributed as a function of task difficulty. This dissects the notion of general intelligence into two non-populational measures, generality and capability, which we apply to individuals and groups of humans, other animals and AI systems, on several cognitive and perceptual tests. Our results indicate that generality and capability can decouple at the individual level: very specialised agents can show high capability and vice versa. The metrics also decouple at the population level, and we rarely see diminishing returns in generality for those groups of high capability. We relate the individual measure of generality to traditional notions of general intelligence and cognitive efficiency in humans, collectives, non-human animals and machines. The choice of the difficulty function now plays a prominent role in this new conception of generality, which brings a quantitative tool for shedding light on long-standing questions about the evolution of general intelligence and the evaluation of progress in Artificial General Intelligence.

Primary Cognitive Categories Are Determined by Their Invariances

The world as we perceive it is structured into objects, actions and places that form parts of events. In this article, my aim is to explain why these categories are cognitively primary. From an empiricist and evolutionary standpoint, it is argued that the reduction of the complexity of sensory signals is based on the brain's capacity to identify various types of invariances that are evolutionarily relevant for the activities of the organism. The first aim of the article is to explain why places, object and actions are primary cognitive categories in our constructions of the external world. It is shown that the invariances that determine these categories have their separate characteristics and that they are, by and large, independent of each other. This separation is supported by what is known about the neural mechanisms. The second aim is to show that the category of events can be analyzed as being constituted of the primary categories. The category of numbers is briefly discussed. Some implications for computational models of the categories are also presented.