Cognitive Design for Artificial Minds

Antonio Lieto

• Verlag: Routledge
• Jahr: 2021
• ISBN:
  9781315460512
• Auflage: 1
• Thema: Computer Science
• Thema: Artificial Intelligence (AI) & Semantics

Cognitive Design for Artificial Minds explains the crucial role that human cognition research plays in the design and realization of artificial intelligence systems, illustrating the steps necessary for the design of artificial models of cognition. It bridges the gap between the theoretical, experimental, and technological issues addressed in the context of AI of cognitive inspiration and computational cognitive science.

Beginning with an overview of the historical, methodological, and technical issues in the field of cognitively inspired artificial intelligence, Lieto illustrates how the cognitive design approach has an important role to play in the development of intelligent AI technologies and plausible computational models of cognition. Introducing a unique perspective that draws upon Cybernetics and early AI principles, Lieto emphasizes the need for an equivalence between cognitive processes and implemented AI procedures, in order to realize biologically and cognitively inspired artificial minds. He also introduces the Minimal Cognitive Grid, a pragmatic method to rank the different degrees of biological and cognitive accuracy of artificial systems in order to project and predict their explanatory power with respect to the natural systems taken as a source of inspiration.

Providing a comprehensive overview of cognitive design principles in constructing artificial minds, this text will be essential reading for students and researchers of artificial intelligence and cognitive science.

1

Cognitive science and artificial intelligence

Death and rebirth of a collaboration

Abstract

The first chapter proposes a brief historical overview of some of the main insights developed over 65 years of research in Artificial Intelligence (AI), by introducing the early vision of the discipline (based on a mutual collaboration with Cognitive Psychology) and its “paradigm shift”, which started from the mid-1980s of the last century. Starting from that period on, AI and the interdisciplinary enterprise known as Cognitive Science started to produce several sub-fields, each with its own goals, methods, and criteria for evaluation. The reasons for the current renewed interest of a cognitively inspired approach in AI research are discussed.

When Cognitive Science was AI

Cognitive Science and Artificial Intelligence (AI) are, nowadays, scientific research fields each endowed with a specific autonomy and research agenda. According to the Oxford Dictionary, the term “Artificial Intelligence” is defined as “the theory and development of computer systems able to perform tasks normally requiring human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages”, while “Cognitive Science” is defined as “the study of thought, learning, and mental organization, which draws on aspects of psychology, linguistics, philosophy, and computer modelling”.

Despite the current different focuses and objectives of each, these two disciplines have many common interests and share the idea of studying the “mind”, its emergent properties, and its functioning in natural and artificial systems, respectively.

The history of these two research fields is, in fact, strongly interconnected. Research in AI – the birth of which dates back to the now-legendary “Dartmouth Workshop” (McCarthy et al., 1955) held in the summer of 1956¹ – has, indeed, been historically inspired by the experimental research in psychology.² Notable examples of such intellectual connections are represented by the early AI systems/frameworks developed until the 1980s. Most of them, indeed, were explicitly designed with a “cognitively oriented” inspiration. In the following sections, we briefly present few famous examples of such systems and formalisms (though the list is far from being exhaustive) with the aim of introducing some of the main modelling paradigms and assumptions that have characterized, and still characterize, the research in AI and cognitive modelling. Each of the systems/formalisms reviewed below can be considered important either because they have achieved some important milestones in terms of performances or because has introduced some relevant ideas that have fostered meaningful developments in the study and the realization of “artificial minds”.

From the general problem-solver to the society of mind: cognitivist insights from the early AI era

One of the first developed AI systems, at the end of the 1950s, is the pioneering work of Herbert Simon, John Clifford Shaw, and Allen Newell on the General Problem Solver (GPS). GPS was a system able to demonstrate simple logic theorems and its decision strategies were explicitly inspired by human verbal protocols³ (Newell, Shaw & Simon, 1959). The underlying idea of this approach was that the computer system had to approximate the decision operations described by humans in their verbal descriptions as closely as possible. In this way, when the program ran on the computer, it would be possible to identify its problems, compare them with the description of the human verbalization, and modify them to improve its performance. In particular, the GPS system was able to implement a key mechanism in human problem solving: the well-known “means-ends analysis” (or M-E heuristics). The M-E heuristics implemented in GPS works as follows: the problem solver makes a comparison between the current situation and a goal situation; then, it computes and evaluate the “distance” between these two states and tries to find, in memory, suitable operators able to reduce such difference. Once a suitable operator is found, it is then applied to change the current situation. The process is repeated until the goal is gradually attained via a process of progressive distance reduction. There are, however, generally no guarantees that the process will succeed. This kind of heuristic was also used to solve, in the decades to come, problems in a number of domains. In order to be executed, in fact, it “only” required an explicit domain representation of the problem to solve (a problem space), operators to move through the space, and information about which operators were relevant for reducing which differences.⁴ GPS can be arguably considered the first cognitively inspired AI system ever developed.

1 The organisers of this even were some “giants” of the history of the Computer Science field from the last century: John McCarthy, Marvin Minsky, Nathaniel Rochester, and Claude Shannon. The workshop, during which McCarthy proposed the use of the term “artificial intelligence” to identify the new emerging discipline, ran for several weeks and saw the participation of many researchers. The notes taken by Ray Solomonoff (one of the participants at the workshop) are available online at http://raysolomonoff.com/dartmouth/.

2 It must be noted that, at that time, there wasn’t a “Cognitive Science” field. However, all the disciplines (philosophy, psychology, computer science, anthropology, linguistics, and ­neurophysiology) and the cultural elements that would have later be called upon to form the interdisciplinary field of “Cognitive Science” were already present.

3 This technique is also known as the “thinking aloud protocol” in the psychological literature (Ericsson & Simon, 1980) and consists of recording the verbal explanations provided by people while executing a given laboratory task.

4 As we will see in more detail in the following sections, the ingredients required for the execution of this kind of heuristic strategy – essentially based on a “search space” approach to problem solving – explicitly supported the so-called “symbolic approach” for the study, analysis, execution, and replication of intelligent behaviour in artificial systems.

A decade after the development of GPS, a Ph.D. student of Herbert Simon⁵ at Carnegie Mellon University (then still named Carnegie Institute of Technology) – Ross Quillian – developed another influential idea in the context of AI of cognitive inspiration; he invented the Semantic Networks: a psychologically plausible model of human semantic memory implemented in a computer system. The idea (Quillian, 1968) was that human memory is associative in nature and that concepts are represented as sort of nodes in graphs and are activated through a mechanism of “spreading activation”, implemented through a marker passing algorithm, allowing the propagation of information through the network to determine the strength of the relationships between concepts. In this setting, the higher the activation of a node in the network, the more contextually relevant that node/concept was assumed to be for the task in focus. Interestingly enough, the research on Semantic Networks paved the way for both the development of the first graph-like, knowledge-based systems and formalisms (which make use of so-called symbolic representations) as well as the improvement of the so-called connectionist or sub-symbolic systems, since the concept of “spreading activation” has been very influential in the context of the “connectionist” investigations (see Cordeschi, 2002: 235, on this point). Before proceeding further with our examples of early cognitively inspired AI systems, it is necessary to briefly introduce the above-mentioned basic notions of “symbolic representations” (and paradigm) and “connectionist or sub-symbolic representations” (and paradigm), since they have been, and still are, really crucial modelling methods in both the past and present AI and cognitive modelling communities. In particular, the notion of “symbolic representation” constitutes a core assumption of the so-called “symbolic paradigm” in AI and cognitive science (which will be better clarified in more detail later in the book). In short, according to this view, intelligence in natural and artificial systems is associated with the capability of storing and manipulating the information in terms of abstract “symbols” (representing, in many cases, some mental proxy associated with external physical objects) and on the capability of executing mental operations and calculations over such symbols. This view was (is) severely criticized by the so-called “connectionist or sub-symbolic paradigm”, according to which the organization of the “mental content” in natural and artificial systems is not based on any symbolic structure but is, on the other hand, (1) distributed in nature and (2) based on parallel models of computations (these are the two core assumptions of the “connectionist representations”), in a way that is more similar to the biological organization and processing mechanisms of neurons and synapses in our brain. From a modelling perspective, this approach has led to the development of the Artificial Neural Networks, or ANNs (partially inspired by the biological neural structure of our brain), and self-organizing systems. We will discuss later the impact of “neural” or brain-inspired methods in early (and modern) AI research.⁶ For the moment it is probably worth mentioning that, from a historical point of view, the “symbolic paradigm” represented the mainstream assumption in the context of both early AI and cognitive modelling research.

5 Herbert Simon is arguably one of the most important scientists of the last century. His influence, indeed, went well beyond his original training in cognitive psychology. Simon was awarded a Nobel Prize in Economics for his studies on “bounded rationality”, which showed – differing from the classical decision models of the time – how humans are not optimal decision makers. This field of study has led to the development of an entirely new discipline that is nowadays known as “behavioural economics”. In addition, he was one of the founding fathers and main protagonist of the field of AI; along with people like Marvin Minsky, John McCarthy, Allen Newell, Nathaniel Rochester, and many others, he was an active participant in the Dartmouth Workshop. As a result of his “bounded rationality” theory in decision making, he was, one of the first scholars to point out, in both cognitive psychology and AI, the role played by heuristics as decisional shortcuts to solve complex problems. The application of the heuristic approach in the context of AI was one of the reasons behind him winning, in 1975, the Turing Award, together with Allen Newell. The particular meanings attributed to the term “heuristics” in the AI research, will be explained later in this chapter.

6 For the sake of completeness, it is also worth mentioning that within the cognitive modelling and AI communities another paradigm has been historically proposed relying on so-called “analog” or “diagrammatic” representations. In particular, according to the supporters of this school of thought, mental representations take the form of “pictures” in the mind. There are many different examples of analog representations proposed, one of the most famous corresponding to the “mental models” by Johnson-Laird (1983, 2006). A general underlying assumption of this class of representation is that “spatial cognition” abilities (represented via these “picture-like” schemas) are a core aspect of natural cognitive systems from which other intelligent mechanisms emerge (e.g., the mental models by Johnson Laird have been notoriously proposed to model different types of inferences).

A confirmation of what was just discussed is provided by the next example of a cognitively inspired AI framework, which we are going to investigate: the notion of Frames (still a symbolic representational framework) operated by Marvin Minsky almost a decade after Quillian’s proposal (Minsky, 1975). With this proposal, Minsky intended to attack another well-known “symbolic approach” developed back then: the “logicist”⁷ position à la McCarthy for the representation of knowledge in artificial systems. In particular, Minsky argued that such a proposal was not able to deal with the flexibility of the commonsense reasoning that is so evident in human beings. Frames, on the other hand, were proposed for endowing AI systems with commonsense knowledge (including default knowledge) about the external world.⁸ The type of knowledge organization proposed in the Frames enabled the first AI systems to extend their automated reasoning abilities from classical deduction to more complicated forms of commonsense and defeasible reasoning (going from induction to abduction). In this case, the idea of the Frames was directly inspired by the work of the psychologist Eleanor Rosch (Rosch, 1975) about the organization of conceptual information in humans known as the “prototype theory”⁹ as well as by the memory “schemas” proposed by the cognitive psychologist Bartlett (Bartlett, 1958). A simple example and use case, done by Minsky himself, of a frame data structure is the following: let us imagine opening a door inside a house we are not familiar with. In this case, we typically expect to find a room that more or less is characterized by features that we have already seen in other rooms we have been in. Such features are referred to as a body of knowledge organized in the form of prototypes (i.e., the typical room). The data structures that reflect this flexible way of using knowledge, which is typical of human beings, can be described as “frame systems”. Therefore, the “room frame” is a chara...

Inhaltsverzeichnis

• Cover
• Half Title
• Title Page
• Copyright Page
• Table of Contents
• List of illustrations
• Introduction
• Acknowledgements
• Dedication
• 1 Cognitive science and artificial intelligence: death and rebirth of a collaboration
• 2 Cognitive and machine-oriented approaches to intelligence in artificial systems
• 3 Principles of the cognitive design approach
• 4 Examples of cognitively inspired systems and application of the Minimal Cognitive Grid
• 5 Evaluating the performances of artificial systems
• 6 The next steps
• References
• Index