Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

In 1974 an article appeared in Science magazine with the dry-sounding title “Judgment Under Uncertainty: Heuristics and Biases” by a pair of psychologists who were not well known outside their discipline of decision theory. In it Amos Tversky and Daniel Kahneman introduced the world to Prospect Theory, which mapped out how humans actually behave when faced with decisions about gains and losses, in contrast to how economists assumed that people behave. Prospect Theory turned Economics on its head by demonstrating through a series of ingenious experiments that people are much more concerned with losses than they are with gains, and that framing a choice from one perspective or the other will result in decisions that are exactly the opposite of each other, even if the outcomes are monetarily the same. Prospect Theory led cognitive psychology in a new direction that began to uncover other human biases in thinking that are probably not learned but are part of our brain’s wiring.

Thinking fast and slow.

This article reviews a diverse set of proposals for dual processing in higher cognition within largely disconnected literatures in cognitive and social psychology. All these theories have in common the distinction between cognitive processes that are fast, automatic, and unconscious and those that are slow, deliberative, and conscious. A number of authors have recently suggested that there may be two architecturally (and evolutionarily) distinct cognitive systems underlying these dual-process accounts. However, it emerges that (a) there are multiple kinds of implicit processes described by different theorists and (b) not all of the proposed attributes of the two kinds of processing can be sensibly mapped on to two systems as currently conceived. It is suggested that while some dual-process theories are concerned with parallel competing processes involving explicit and implicit knowledge systems, others are concerned with the influence of preconscious processes that contextualize and shape deliberative reasoning and decision-making.

/pdf/dual-processing-accounts-of-reasoning-judgment-and-social-118hw7hde7.pdf

Dual-Processing Accounts of Reasoning, Judgment, and Social Cognition

Emotion and Adaptation

The emerging viewpoint of embodied cognition holds that cognitive processes are deeply rooted in the body’s interactions with the world. This position actually houses a number of distinct claims, some of which are more controversial than others. This paper distinguishes and evaluates the following six claims: (1) cognition is situated; (2) cognition is time-pressured; (3) we off-load cognitive work onto the environment; (4) the environment is part of the cognitive system; (5) cognition is for action; (6) offline cognition is body based. Of these, the first three and the fifth appear to be at least partially true, and their usefulness is best evaluated in terms of the range of their applicability. The fourth claim, I argue, is deeply problematic. The sixth claim has received the least attention in the literature on embodied cognition, but it may in fact be the best documented and most powerful of the six claims.

/pdf/six-views-of-embodied-cognition-2l6klwi201.pdf

Six views of embodied cognition.

The advent of software agents gave rise to much discussion of just what such an agent is, and of how they differ from programs in general. Here we propose a formal definition of an autonomous agent which clearly distinguishes a software agent from just any program. We also offer the beginnings of a natural kinds taxonomy of autonomous agents, and discuss possibilities for further classification. Finally, we discuss subagents and multiagent systems.

/pdf/is-it-an-agent-or-just-a-program-a-taxonomy-for-autonomous-oncwlzq0wr.pdf

Is it an Agent, or Just a Program?: A Taxonomy for Autonomous Agents

http://cogprints.org/5854/1/TICSarticle2003.pdf

How conscious experience and working memory interact

/pdf/spaces-in-which-sequences-suffice-2y3u7yqx7i.pdf

Spaces in which sequences suffice

From the Publisher:
Stan Franklin is the perfect tour guide through the contemporary interdisciplinary matrix of artificial intelligence, cognitive science, cognitive neuroscience, artificial neural networks, artificial life, and robotics that is producing a new paradigm of mind. Along the way, Franklin makes the case for a perspective that rejects a rigid distinction between mind and non-mind in favor of a continuum from less to more mind, and for the role of mind as a control structure with the essential task of choosing the next action. Selected stops include the best of the work in these different fields, with the key concepts and results explained in just enough detail to allow readers to decide for themselves why the work is significant. Major attractions include animal minds, Newell's SOAR, the three Artificial Intelligence debates, Holland's genetic algorithms, Wilson's Animat, Brooks' subsumption architecture, Jackson's pandemonium architecture, Ornstein's multimind, Minsky's society of mind, Maes's behavior networks, Edelman's neural Darwinism, Drescher's schema mechanisms, Kanerva's sparse distributed memory, Hofstadter and Mitchell's Copycat, and Agre and Chapman's deictic representations.

Artificial Minds

A global workspace is a hub of binding and propagation in a population of loosely coupled signaling elements. Global workspace (GW) architectures recruit many distributed, specialized agents to help resolve focal ambiguities. In the brain, conscious experiences may reflect a global workspace function. For animals the natural world is full of fitness-related ambiguities, suggesting a general adaptive pressure for brains to resolve focal ambiguities quickly and accurately. In humans and related species the cortico-thalamic (C-T) core is believed to underlie conscious aspects of perception, thinking, learning, feelings of knowing, emotions, imagery, working memory and executive control. The C-T core has many anatomical hubs, but conscious percepts are unitary and internally consistent at any given moment. The repertoire of conscious contents is a large, open set. These points suggest that a brain-based GW capacity cannot be localized in a single anatomical hub. Rather, it should be sought in a dynamic capacity for adaptive binding and propagation of neural signals over multi-hub networks. We refer to this as dynamic global workspace theory (dGW). In this view, conscious contents can arise in any region of the C-T core when multiple signal streams settle on a winner-take-all equilibrium. The resulting bound gestalt may ignite an any-to-many broadcast, lasting ~100-200 ms, and trigger widespread adaptation in established networks. Binding and broadcasting may involve theta/gamma or alpha/gamma phase coupling. Conscious contents (qualia) may reflect their sources in cortex. Sensory percepts may bind and broadcast from posterior regions, while non-sensory feelings of knowing (FOKs) may be frontotemporal. The small focal capacity of conscious contents may be the biological price to pay for global access. We propose that in the intact brain the hippocampal/rhinal complex may support conscious event organization as well as episodic memory coding.

/pdf/global-workspace-dynamics-cortical-binding-and-propagation-59lfnstswg.pdf

Stan Franklin

Papers

Is it an Agent, or Just a Program?: A Taxonomy for Autonomous Agents

How conscious experience and working memory interact

Spaces in which sequences suffice

Artificial Minds

Global workspace dynamics: cortical "binding and propagation" enables conscious contents.