The Information-Theoretic and Algorithmic Approach to Human, Animal, and Artificial Cognition

Abstract

We survey concepts at the frontier of research connecting artificial, animal and human cognition to computation and information processing-from the Turing test to Searle's Chinese Room argument, from Integrated Information Theory to computational and algorithmic complexity. We start by arguing that passing the Turing test is a trivial computational problem and that its pragmatic difficulty sheds light on the computational nature of the human mind more than it does on the challenge of artificial intelligence. We then review our proposed algorithmic information-theoretic measures for quantifying and characterizing cognition in various forms. These are capable of accounting for known biases in human behavior, thus vindicating a computational algorithmic view of cognition as first suggested by Turing, but this time rooted in the concept of algorithmic probability, which in turn is based on computational universality while being independent of computational model, and which has the virtue of being predictive and testable as a model theory of cognitive behavior.

Mathematics as Information Compression via the Matching and Unification of Patterns

“…Another area of research which aims to develop new insights into the nature of human cognition is Algorithmic Cognition (see, for example, [47,48]). is perspective takes advantage of insights gained in the development of ALP (with Bayes' eorem) and AIT (Section 4.2).…”

From Reflex to Reflection: Two Tricks AI Could Learn from Us

“…At a lower level, the reconstruction of partially hidden patterns seems to obey a principle of minimum Kolmogorov complexity [40]. Conversely, when human subjects are asked to exhibit random behavior by producing what they regard as unintelligible, structureless sequences, they do so by maximizing the complexity of their responses [42]. The cognitive importance of Kolmogorov complexity, however, is not limited to its role in guiding intelligent processing, as in learning, in analogy making or in structure detection.…”

Low-algorithmic-complexity entropy-deceiving graphs

“…Rectifying the approaches based on models of maximum entropy involves updating and replacing the assumption of the maximum entropy ensemble. An example illustrating how to achieve this in the context of, e.g., a Bayesian approach, has been provided in [45] and consists in replacing the uninformative prior by the uninformative algorithmic probability distribution, the so-called Universal Distribution, as introduced by Levin [20]. The general approach has already delivered some important results [46] by, e.g., quantifying the degree of human cognitive randomness that previous statistical approaches and measures such as Entropy made it impossible to quantify.…”