A cognitive architecture is a blueprint for intelligent agents. It proposes (artificial) computational processes that act like certain cognitive systems, most often, like a person, or acts intelligent under some definition. It is a superset of general agent architectures. The term architecture implies an approach that attempts to model not only behavior, but also structural properties of the modelled system. Simple reflex agent Learning agent In computer science, an intelligent agent (IA) is a software agent that exhibits some form of artificial intelligence. ... To meet Wikipedias quality standards, this article or section may require cleanup. ... Intelligence is the mental capacity to reason, plan, solve problems, think abstractly, comprehend ideas and language, and learn. ... In computer science, agent architecture reveres to the blueprints of software agents and intelligent control systems, depicting the arrangement of components. ...

Characterization

Common to cognitive architecture is the belief that understanding (human) cognitive processing means being able to implement them on a computational level. Cognitive architectures can be characterized by certain properties or goals that are as follows:

1. Implementation of not just various different aspects of cognitive behavior but of cognition as a whole (Holism, e.g. Unified theory of cognition). This is in contrast to cognitive models.
2. The architecture often tries to reproduce the behavior of the modelled system (human), in a way that timely behavior (reaction times) of the architecture and modelled cognitive systems can be compared in detail.
3. Robust behavior in the face of error, the unexpected, and the unknown. (see Graceful degradation).
4. Learning (not for all cognitive architectures)
5. Parameter-free: The system does not depend on parameter tuning (in contrast to Artificial neural networks) (not for all cognitive architectures)

It is important to note that cognitive architectures don't have to follow a top-down approach to cognition (cf. Top-down and bottom-up design). Holism (from holos, a Greek word meaning all, entire, total) is the idea that all the properties of a given system (biological, chemical, social, economic, mental, linguistic, etc. ... Unified theories of cognition is a book written by Allen Newell in 1987. ... The term cognitive model can have basically two meanings. ... Behaviorism or behaviourism is an approach to psychology based on the proposition that behavior can be researched scientifically without recourse to inner mental states. ... For a reflex, reaction time is the time from the onset of a stimulus until the organism responds. ... In the context of computer software, robustness is the resilience of the system, especially when under stress or when confronted with invalid input. ... Graceful degradation is a property of a computer system whereby it reacts safely and proportionately to erroneous or unexpected circumstances. ... To meet Wikipedias quality standards, this article or section may require cleanup. ... The factual accuracy of this article is disputed. ... A neural network is an interconnected group of neurons. ... Top-down and bottom-up are strategies of information processing, mostly involving software, and by extension other humanistic and scientific systems theory. ...

Distinctions

Cognitive architectures can be symbolic, connectionist, or hybrid. Some cognitive architectures or models base on a set of generic rules, as, e.g., the Information Processing Language (such as e.g. Soar based on the unified theory of cognition, or similarly ACT). Many of these architectures are based on the-mind-is-like-a-computer analogy. In contrast subsymbolic processing specifies no such rules a priori and relies on emergent properties of processing units (e.g. nodes). A further distinction is whether the architecture is centralized with a neural correlate of a processor at its core, or decentralized (distributed). The decentralized flavor, has become popular under the name of parallel distributed processing in mid-1980s and connectionism, a prime example being neural networks. A further design issue is additionally a decision between holistic and atomism, or (more concrete) modular in structure. By analogy, this extends to issues of knowledge representation. Connectionism is an approach in the fields of artificial intelligence, cognitive science, neuroscience, psychology and philosophy of mind. ... In this article intelligent system is refers to an IEEE magazine [1]. It is also the name of a video game developer and internal team of Nintendo Co. ... In psychology, cognitivism is a theoretical approach to understanding the mind, which argues that mental function can be understood by quantitative, positivist and scientific methods, and that such functions can be described as information processing models. ... Information Processing Language (IPL) is a programming language developed by Allen Newell, Cliff Shaw, and Herbert Simon at RAND Corporation and the Carnegie Institute of Technology from about 1956. ... Soar (also known as SOAR) is a symbolic cognitive architecture, created by John Laird, Allen Newell, and Paul Rosenbloom at Carnegie Mellon University. ... Unified theories of cognition is a book written by Allen Newell in 1987. ... ACT-R is a cognitive architecture developed by John R Anderson. ... The term node can refer to: Node, a spatial locus along a standing wave where the wave has minimal amplitude. ... Centralization is the process by which the activities of an organization, particularly those regarding decision-making, become concentrated within a particular location and/or group. ... A CPU The processor sub-system of a data processing system processes received information after it has been encoded into data by the input sub-system. ... Decentralisation (or decentralization) is any of various means of more widely distributing decision-making to bring it closer to the point of service or action. ... Connectionism today generally refers to an approach in the fields of cognitive psychology, cognitive science and philosophy of mind which models mental or behavioral phenomena with neural networks, and is associated with a certain set of arguments for why this is a good idea. ... The examples and perspective in this article or section may not represent a worldwide view. ... Connectionism is an approach in the fields of artificial intelligence, cognitive science, neuroscience, psychology and philosophy of mind. ... Simplified view of an artificial neural network A neural network is a system of interconnecting neurons in a network working together to produce an output function. ... Holism (from holos, a Greek word meaning all, entire, total) is the idea that all the properties of a given system (biological, chemical, social, economic, mental, linguistic, etc. ... In natural philosophy, atomism is the theory that all the objects in the universe are composed of very small, indestructible elements - atoms. ... Modularity is a concept that has applications in the contexts of computer science, particularly programming, as well as cognitive science in investigating the structure of mind. ... Knowledge representation is a research and application domain in artificial intelligence, cognitive science, as well as in the knowledge management & knowledge engineering. ...

In traditional AI, intelligence is often programmed from above: the programmer is the creator, and makes something and imbues it with its intelligence. Biologically-inspired computing, on the other hand, takes sometimes a more bottom-up, decentralised approach; bio-inspired techniques often involve the method of specifying a set of simple generic rules or a set of simple nodes, from the interaction of which emerges the overall behavior. It is hoped to build up complexity until the end result is something markedly complex (see complex systems). // Hondas intelligent humanoid robot AI redirects here. ... Intelligence is the mental capacity to reason, plan, solve problems, think abstractly, comprehend ideas and language, and learn. ... Creationism is generally the belief that the universe was created by a deity, or alternatively by one or more powerful and intelligent beings. ... Biologically-inspired computing (also bio-inspired computing) is a field of study that loosely knits together subfields related to the topics of connectionism, social behaviour and emergence. ... Top-down and bottom-up are strategies of information processing, mostly involving software, and by extension other humanistic and scientific systems theory. ... Decentralisation (American: decentralization) is any of various means of more widely distributing decision-making to bring it closer to the point of service or action. ... The term node can refer to: Node, a spatial locus along a standing wave where the wave has minimal amplitude. ... A termite cathedral mound produced by a termite colony: a classic example of emergence in nature. ... For the Computer Science term, see Computational complexity theory. ... There are many definitions of complexity, therefore many natural, artificial and abstract objects or networks can be considered to be complex systems, and their study (complexity science) is highly interdisciplinary. ...

Some famous cognitive architectures

• ACT-R, developed at Carnegie Mellon University under John R. Anderson.
• Soar, developed under Allen Newell and John Laird at Carnegie Mellon University and the University of Michigan.
• EPIC, developed under David E. Kieras and David E. Meyer at the University of Michigan
• Copycat, by Douglas Hofstadter and Melanie Mitchell at the Indiana University, Bloomington.
• DUAL, developed at the New Bulgarian University under Boicho Kokinov.
• Apex developed under Michael Freed at NASA Ames Research Center.
• Psi developed under Dietrich Dörner at the Otto-Friedrich University in Bamberg, Germany.
• PRODIGY, by Veloso et al.
• Subsumption architectures, developed e.g. by Rodney Brooks (though it could be argued whether they are cognitive)

ACT-R (pronounced actor) is a symbolic cognitive architecture, created by John R. Anderson and others at Carnegie-Mellon University. ... To meet Wikipedias quality standards, this article or section may require cleanup. ... John Robert Anderson (born 1947 in Vancouver, British Columbia) is a professor of psychology and computer science at Carnegie Mellon University. ... Soar (also known as SOAR) is a symbolic cognitive architecture, created by John Laird, Allen Newell, and Paul Rosenbloom at Carnegie Mellon University. ... Allen Newell (March 19, 1927 - July 19, 1992) was a researcher in computer science and cognitive psychology at the RAND corporation and at Carnegie-Mellon’s School of Computer Science. ... To meet Wikipedias quality standards, this article or section may require cleanup. ... UM also has campuses in Dearborn and Flint. ... EPIC (Executive-Process/Interactive Control) is a cognitive architecture developed by David E. Kieras and David E. Meyer at the University of Michigan. ... UM also has campuses in Dearborn and Flint. ... Copycat is a model of analogy making and human cognition based on the concept of the parallel terraced scan, developed by Douglas Hofstadter, Melanie Mitchell, and others at the at Center for Research on Concepts and Cognition, Indiana University at Bloomington. ... Douglas Richard Hofstadter (born February 15, 1945) is an American academic. ... Melanie Mitchell is a scientist who has worked at the Santa Fe Institute and Los Alamos National Laboratory. ... Indiana University Bloomington is the principal campus of the Indiana University system. ... DUAL ia a general cognitive architecture integrating the connectionist and symbolic approaches at the micro level. ... New Bulgarian University (Нов български университет, abbreviated as НБУ, NBU) is a private institution of higher education based in Sofia, the capital of Bulgaria. ... Boicho Kokinov received his PhD at the Bulgarian Academy of Sciences, Sofia. ... Aerial View of Moffett Field and NASA Ames Research Center. ... Prof. ... For other meanings, see Bamberg (disambiguation). ... Subsumption architecture is an AI concept originating from behavior based robotics. ... Rodney Allen Brooks (b. ...

See also

• Cognitive science
• Strong AI
• Artificial consciousness
• Autonomous agent
• production system
• unified theory of cognition
• High Yield Cognitive Systems

Rendering of human brain based on MRI data Cognitive science is usually defined as the scientific study either of mind or of intelligence (e. ... In the philosophy of artificial intelligence, strong AI is the supposition that some forms of artificial intelligence can truly reason and solve problems; strong AI supposes that it is possible for machines to become sapient, or self-aware, but may or may not exhibit human-like thought processes. ... To meet Wikipedias quality standards, this article or section may require cleanup. ... An autonomous agent is a system situated in, and part of, an environment, which senses that environment, and acts on it, over time, in pursuit of its own agenda. ... A production system consists of a collection of productions (rules), a working memory of facts and an algorithm, known as forward chaining, for producing new facts from old. ... Unified theories of cognition is a book written by Allen Newell in 1987. ... In 2002, the Defense Advanced Research Projects Agency (DARPA) Information Processing Technology Office (IPTO) outlined a unified vision for the future of computing technologies that possess human-like information processing capabilities in its Broad Agency Announcement 02-21 . ...

External links

• categorized publications about ACT-R
• A Survey of Cognitive and Agent Architectures
• Architecture-Based Conceptions of Mind research paper pdf by Aaron Sloman, University of Birmingham. The ideas are summarised in this PDF presentation on Architectures for Human-like Agents.