Measuring Intelligence in Natural and Artificial Systems

We propose a novel framework for quantifying intelligence based on the principles of thermodynamics and information theory. Our framework defines intelligence as the efficiency with which a system can use energy to maintain a non-equilibrium state and perform adaptive, goal-directed behavior. We introduce a quantitative measure of intelligence, I, which captures the system's ability to deviate from the principle of least action and maintain a non-equilibrium distribution of microstates. We derive this measure using the concepts of entropy, mutual information, and Kullback-Leibler divergence, and show how it can be applied to various physical, biological, and artificial systems. Our framework provides a unified, scale-invariant way of understanding and comparing intelligence across diverse domains, and suggests new approaches for designing and optimizing intelligent systems.

This paper proposes a comprehensive framework for understanding intelligence and subjective experience, integrating concepts from thermodynamics, information theory, complexity theory, reinforcement learning, and complex systems theory. The framework defines intelligence as a function of a system's energy, entropy, information, complexity, goalachievement, and learning capacity, while subjective experience is described as a dynamic interplay between the system's internal states, its model of the environment, and its interactions with the world. We present a set of equations that capture the relationships between these key variables and processes, providing a foundation for further research, computational modeling, and philosophical exploration of these fundamental phenomena. The framework aims to bridge the gap between various disciplines and offer a unified perspective on the emergence of intelligence and consciousness in complex systems, from biological brains to artificial agents. By formalizing these concepts and their interactions, we hope to stimulate new insights, testable hypotheses, and interdisciplinary collaborations in the study of mind and intelligence.

Frontiers in Systems Neuroscience, 2019

In today's society, it becomes increasingly important to assess which non-human and non-verbal beings possess consciousness. This review article aims to delineate criteria for consciousness especially in animals, while also taking into account intelligent artifacts. First, we circumscribe what we mean with "consciousness" and describe key features of subjective experience: qualitative richness, situatedness, intentionality and interpretation, integration and the combination of dynamic and stabilizing properties. We argue that consciousness has a biological function, which is to present the subject with a multimodal, situational survey of the surrounding world and body, subserving complex decision-making and goal-directed behavior. This survey reflects the brain's capacity for internal modeling of external events underlying changes in sensory state. Next, we follow an inside-out approach: how can the features of conscious experience, correlating to mechanisms inside the brain, be logically coupled to externally observable ("outside") properties? Instead of proposing criteria that would each define a "hard" threshold for consciousness, we outline six indicators: (i) goal-directed behavior and model-based learning; (ii) anatomic and physiological substrates for generating integrative multimodal representations; (iii) psychometrics and meta-cognition; (iv) episodic memory; (v) susceptibility to illusions and multistable perception; and (vi) specific visuospatial behaviors. Rather than emphasizing a particular indicator as being decisive, we propose that the consistency amongst these indicators can serve to assess consciousness in particular species. The integration of scores on the various indicators yields an overall, graded criterion for consciousness, somewhat comparable to the Glasgow Coma Scale for unresponsive patients. When considering theoretically derived measures of consciousness, it is argued that their validity should not be assessed on the basis of a single quantifiable measure, but requires cross-examination across multiple pieces of evidence, including the indicators proposed here. Current intelligent machines, including deep learning neural networks (DLNNs) and agile robots, are not indicated to be conscious yet. Instead of assessing machine consciousness by a brief Turing-type of test, evidence for it may gradually accumulate when we study machines ethologically Frontiers in Systems Neuroscience | www.frontiersin.org 1

Proceedings of the 2001 PerMIS, NIST Special Publication 982, September 2001., 2002

Is the measurement of performance for intelligent systems different than that of non-intelligent systems? In this white paper, we explore the various dimensions of evaluation of intelligence and performance. The main areas we tackle are the testing of intelligent systems, performance evaluation in the non-numerical domain, and the mathematical and computational premises of evaluations.

1992

A method of measuring intelligence quantitatively in units of bits based on information theory is presented. The proposed definition of intelligence gives only a quantitative measure of the thinking process distinguishable from the information processing part and knowledge. It also treats intelligence as a resource and predicts that a C compiler uses more intelligence per instruction than a Spice program. The term `capability for intelligence' is introduced and shows that a human being may have a much higher capability for intelligence than a microprocessor. The amount of intelligence measured can be used to develop more intelligent microprocessors and algorithms

Cornell University - arXiv, 2022

In popular media, there is often a connection drawn between the advent of awareness in artificial agents and those same agents simultaneously achieving human or superhuman level intelligence. In this work, we explore the validity and potential application of this seemingly intuitive link between consciousness and intelligence. We do so by examining the cognitive abilities associated with three contemporary theories of conscious function: Global Workspace Theory (GWT), Information Generation Theory (IGT), and Attention Schema Theory (AST). We find that all three theories specifically relate conscious function to some aspect of domain-general intelligence in humans. With this insight, we turn to the field of Artificial Intelligence (AI) and find that, while still far from demonstrating general intelligence, many state-of-the-art deep learning methods have begun to incorporate key aspects of each of the three functional theories. Having identified this trend, we use the motivating example of mental time travel in humans to propose ways in which insights from each of the three theories may be combined into a single unified and implementable model. Given that it is made possible by cognitive abilities underlying each of the three functional theories, artificial agents capable of mental time travel would not only possess greater general intelligence than current approaches, but also be more consistent with our current understanding of the functional role of consciousness in humans, thus making it a promising near-term goal for AI research.

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.

Bulletin of the Psychonomic Society, 1993

What is it that makes human beings so good at fuzzy judgments and so poor at precise computation? This paper first addresses this question in the context of a biofunctional theory of how the nervous system functions and then discusses a fuzzy intelligence evaluation system for determing the intelligence of individuals.

In this paper, we propose a novel approach to understanding intelligence based on the principles of thermodynamics and information theory. We define intelligence as the energy required to produce observed deviations from the expected behavior of a system, and we show how this definition can be formalized using the concepts of entropy and information processing.

2021

This paper addresses what we consider to be the most pressing challenge for the emerging science of consciousness: the measurement problem of consciousness. That is, by what methods can we determine the presence of and properties of consciousness? Most methods are currently developed through evaluation of the presence of consciousness in humans and here we argue that there are particular problems in application of these methods to nonhuman cases-what we call the indicator validity problem and the extrapolation problem. The first is a problem with the application of indicators developed using the differences in conscious and unconscious processing in humans to the identification of other conscious vs. non-conscious organisms or systems. The second is a problem in extrapolating any indicators developed in humans or other organisms to artificial systems. However, while pressing ethical concerns add urgency in the attribution of consciousness and its attendant moral status to non-human animals and intelligent machines, we cannot wait for certainty and we advocate the use of a precautionary principle to avoid doing unintentional harm. We also intend that the considerations and limitations discussed in this paper can be used to further analyse and refine the methods of consciousness science with the hope that one day we may be able to solve the measurement problem of consciousness.