Soar (cognitive architecture)
Information about Soar (cognitive architecture)
Soar (originally known as SOAR) is a symbolic cognitive architecture, created by John Laird, Allen Newell, and Paul Rosenbloom at Carnegie Mellon University. It is both a view of what cognition is and an implementation of that view through a computer programming architecture for Artificial Intelligence (AI). Since its beginnings in 1983 and its presentation on a paper in 1987 it has been widely used by AI researchers to model different aspects of human behavior.
The main goal of the Soar project is to be able to handle the full range of capabilities of an intelligent agent, from highly routine to extremely difficult open-ended problems. In order for that to happen, according to the view underlying Soar, it needs to be able to create representations and use appropriate forms of knowledge (such as procedural, declarative, episodic, and possibly iconic). Soar should then address a collection of mechanisms of the mind. Also underlying the Soar architecture is the view that a symbolic system is necessary and sufficient for general intelligence (see brief comment on neats versus scruffies). This is known as the physical symbol system hypothesis. The views of cognition underlying Soar is tied to the psychological theory expressed in Allen Newell's book, Unified Theories of Cognition.
Although the ultimate goal for Soar is to achieve general intelligence, there is no claim that this goal has already been reached. Advocates of the system recognize that Soar is still missing some important aspects of intelligence. Currently there are projects underway to add episodic and semantic memories to Soar as well as support for emotions. Some additional examples of missing capabilities include automatically creating new representations on its own, such as through hierarchical clustering.
Soar is based on a production system, i.e. it uses explicit production rules to govern its behavior (these are roughly of the form "if... then...", as also used in expert systems). Problem solving can be roughly described as a search through a problem space (the collection of different states which can be reached by the system at a particular time) for a goal state (which represents the solution for the problem). This is implemented by searching for the states which bring the system gradually closer to its goal. Each move consists of a decision cycle which has an elaboration phase (in which a variety of different pieces of knowledge bearing the problem are brought to Soar's working memory) and a decision procedure (which weighs what was found on the previous phase and assigns preferences to ultimately decide the action to be taken).
SOAR originally stood for State, Operator And Result, reflecting this representation of problem solving as the application of an operator to a state to get a result. According to the project FAQ, the Soar development community no longer regards Soar as an acronym so it is no longer spelled all in caps though it is still representative of the core of the implementation.
If the decision procedure just described is not able to determine a unique course of action, Soar may use different strategies, known as weak methods to solve the impasse. These methods are appropriate to situations in which knowledge is not abundant. Some examples are means-ends analysis (which may calculate the difference between each available option and the goal state) and a type of hill-climbing. When a solution is found by one of these methods, Soar uses a learning technique called chunking to transform the course of action taken into a new rule. The new rule can then be applied whenever Soar encounters the situation again (that is, there will be no longer an impasse).
ACT, e.g. ACT-R is another cognitive architecture by John R. Anderson that operates on similar principles. Other cognitive architectures are CLARION, ICARUS, DUAL, and Psi.
The physical symbol system hypothesis was formulated by Newell and Simon (1963) as the result of success of GPS (General Problem Solver) and subsequent programs as models of cognition.
..... Click the link for more information.
The main goal of the Soar project is to be able to handle the full range of capabilities of an intelligent agent, from highly routine to extremely difficult open-ended problems. In order for that to happen, according to the view underlying Soar, it needs to be able to create representations and use appropriate forms of knowledge (such as procedural, declarative, episodic, and possibly iconic). Soar should then address a collection of mechanisms of the mind. Also underlying the Soar architecture is the view that a symbolic system is necessary and sufficient for general intelligence (see brief comment on neats versus scruffies). This is known as the physical symbol system hypothesis. The views of cognition underlying Soar is tied to the psychological theory expressed in Allen Newell's book, Unified Theories of Cognition.
Although the ultimate goal for Soar is to achieve general intelligence, there is no claim that this goal has already been reached. Advocates of the system recognize that Soar is still missing some important aspects of intelligence. Currently there are projects underway to add episodic and semantic memories to Soar as well as support for emotions. Some additional examples of missing capabilities include automatically creating new representations on its own, such as through hierarchical clustering.
Soar is based on a production system, i.e. it uses explicit production rules to govern its behavior (these are roughly of the form "if... then...", as also used in expert systems). Problem solving can be roughly described as a search through a problem space (the collection of different states which can be reached by the system at a particular time) for a goal state (which represents the solution for the problem). This is implemented by searching for the states which bring the system gradually closer to its goal. Each move consists of a decision cycle which has an elaboration phase (in which a variety of different pieces of knowledge bearing the problem are brought to Soar's working memory) and a decision procedure (which weighs what was found on the previous phase and assigns preferences to ultimately decide the action to be taken).
SOAR originally stood for State, Operator And Result, reflecting this representation of problem solving as the application of an operator to a state to get a result. According to the project FAQ, the Soar development community no longer regards Soar as an acronym so it is no longer spelled all in caps though it is still representative of the core of the implementation.
If the decision procedure just described is not able to determine a unique course of action, Soar may use different strategies, known as weak methods to solve the impasse. These methods are appropriate to situations in which knowledge is not abundant. Some examples are means-ends analysis (which may calculate the difference between each available option and the goal state) and a type of hill-climbing. When a solution is found by one of these methods, Soar uses a learning technique called chunking to transform the course of action taken into a new rule. The new rule can then be applied whenever Soar encounters the situation again (that is, there will be no longer an impasse).
ACT, e.g. ACT-R is another cognitive architecture by John R. Anderson that operates on similar principles. Other cognitive architectures are CLARION, ICARUS, DUAL, and Psi.
External links
References
- Lehman, Laird, and Rosenbloom, 2006 A Gentle Introduction to Soar: 2006 update
- Rosenbloom, Laird, and Newell, 1993 The Soar Papers: Readings on Integrated Intelligence
- Newell, 1990, Unified Theories of Cognition, Harvard University Press
- Laird, Rosenbloom, Newell, John and Paul, Allen (1987). "Soar: An Architecture for General Intelligence". Artificial Intelligence, 33: 1-64.
The word cognitivism is used in several ways:
..... Click the link for more information.
- In ethics, cognitivism is the philosophical view that ethical sentences express propositions, and hence are capable of being true or false. See Cognitivism (ethics).
..... Click the link for more information.
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.
..... Click the link for more information.
..... Click the link for more information.
John E. Laird (born March 16, 1954 in Ann Arbor, Michigan) is a computer scientist who, with Paul Rosenbloom and Allen Newell, created the Soar cognitive architecture at Carnegie Mellon University.
..... Click the link for more information.
..... Click the link for more information.
Allen Newell
Born March 19 1927
Died July 19 1992 (aged 65)
Field Computer Science
Cognitive Psychology
..... Click the link for more information.
Born March 19 1927
Died July 19 1992 (aged 65)
Field Computer Science
Cognitive Psychology
..... Click the link for more information.
Carnegie Mellon University is a private research university in Pittsburgh, Pennsylvania, United States. It began as the Carnegie Technical Schools, founded by Andrew Carnegie in 1900. In 1912, the school became Carnegie Institute of Technology and began granting four-year degrees.
..... Click the link for more information.
..... Click the link for more information.
Cognition is a diffuse term, used in different ways by different disciplines. In psychology, it refers to an information processing view of an individual's psychological functions.
..... Click the link for more information.
..... Click the link for more information.
A computer program is one or more instructions that are intended for execution by a computer. Specifically, it is a symbol or combination of symbols forming an algorithm that may or may not terminate, and that algorithm is written in a programming language.
..... Click the link for more information.
..... Click the link for more information.
artificial intelligence (or AI) is "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions which maximizes its chances of success.
..... Click the link for more information.
..... Click the link for more information.
19th century - 20th century - 21st century
1950s 1960s 1970s - 1980s - 1990s 2000s 2010s
1980 1981 1982 - 1983 - 1984 1985 1986
Year 1983 (MCMLXXXIII
..... Click the link for more information.
1950s 1960s 1970s - 1980s - 1990s 2000s 2010s
1980 1981 1982 - 1983 - 1984 1985 1986
Year 1983 (MCMLXXXIII
..... Click the link for more information.
19th century - 20th century - 21st century
1950s 1960s 1970s - 1980s - 1990s 2000s 2010s
1984 1985 1986 - 1987 - 1988 1989 1990
Year 1987 (MCMLXXXVII
..... Click the link for more information.
1950s 1960s 1970s - 1980s - 1990s 2000s 2010s
1984 1985 1986 - 1987 - 1988 1989 1990
Year 1987 (MCMLXXXVII
..... Click the link for more information.
The term cognitive model can have basically two meanings. In cognitive psychology, a model is a simplified representation of reality. The essential quality of such a model is to help deciding the appropriate actions, i.e.
..... Click the link for more information.
..... Click the link for more information.
intelligent agent (IA) is a software agent that assists users and will act on their behalf, in performing non-repetitive computer-related tasks. An agent in the sense of the word is like an insurance agent or travel agent.
..... Click the link for more information.
..... Click the link for more information.
Knowledge representation is an issue that arises in both cognitive science and artificial intelligence. In cognitive science it is concerned with how people store and process information.
..... Click the link for more information.
..... Click the link for more information.
Procedural knowledge is the knowledge exercised in the performance of some task. See below for the specific meaning of this term in cognitive psychology and intellectual property law.
..... Click the link for more information.
..... Click the link for more information.
Descriptive knowledge, also declarative knowledge or propositional knowledge, is the species of knowledge that is, by its very nature, expressed in declarative sentences or indicative propositions.
..... Click the link for more information.
..... Click the link for more information.
Episodic memory refers to the memory of events, times, places, associated emotions, and other conception-based knowledge in relation to an experience. Semantic and episodic memory together make up the category of declarative memory, which is one of the two major divisions in memory.
..... Click the link for more information.
..... Click the link for more information.
MIND High School
Address
4563 St. Urbain
Montreal, Quebec, H2T 2V9, Canada
..... Click the link for more information.
Address
4563 St. Urbain
Montreal, Quebec, H2T 2V9, Canada
..... Click the link for more information.
Intelligence is a property of mind that encompasses many related abilities, such as the capacities to reason, to plan, to solve problems, to think abstractly, to comprehend ideas, to use language, and to learn. There are several ways to define intelligence.
..... Click the link for more information.
..... Click the link for more information.
In artificial intelligence, the labels neats and scruffies are used to refer to one of the continuing philosophical disputes in artificial intelligence research. This conflict is over a serious concern: what is the best way to design an intelligent system? Neats
..... Click the link for more information.
..... Click the link for more information.
- See also:
The physical symbol system hypothesis was formulated by Newell and Simon (1963) as the result of success of GPS (General Problem Solver) and subsequent programs as models of cognition.
..... Click the link for more information.
Allen Newell
Born March 19 1927
Died July 19 1992 (aged 65)
Field Computer Science
Cognitive Psychology
..... Click the link for more information.
Born March 19 1927
Died July 19 1992 (aged 65)
Field Computer Science
Cognitive Psychology
..... Click the link for more information.
Unified theories of cognition is a book written by Allen Newell in 1987. Newell argues for the need of a set of general assumptions for cognitive models that account for all of cognition: a unified theory of cognition (UTC).
..... Click the link for more information.
..... Click the link for more information.
A production system (or production rule system) is a computer program typically used to provide some form of artificial intelligence, which consists primarily of a set of rules about behavior.
..... Click the link for more information.
..... Click the link for more information.
An expert system, also known as a knowledge based system, is a computer program that contains some of the subject-specific knowledge, and contains the knowledge and analytical skills of one or more human experts.
..... Click the link for more information.
..... Click the link for more information.
Working memory is a theoretical framework within cognitive psychology that refers to the structures and processes used for temporarily storing and manipulating information.
..... Click the link for more information.
..... Click the link for more information.
Means-Ends Analysis (MEA) is a technique used in Artificial Intelligence for controlling search in problem solving computer programs.
It is also a technique used at least since the 1950s as a creativity tool, most frequently mentioned in engineering books on design methods.
..... Click the link for more information.
It is also a technique used at least since the 1950s as a creativity tool, most frequently mentioned in engineering books on design methods.
..... Click the link for more information.
In computing, optimization is the process of modifying a system to make some aspect of it work more efficiently or use fewer resources. For instance, a computer program may be optimized so that it executes more rapidly, or is capable of operating within a reduced amount of memory
..... Click the link for more information.
..... Click the link for more information.
In cognitive psychology and mnemonics, chunking refers to a strategy for making more efficient use of short-term memory by recoding information. More generally, Herbert Simon has used the term chunk
..... Click the link for more information.
..... Click the link for more information.
ACT-R (pronounced act-ARE: Adaptive Control of Thought--Rational) is a cognitive architecture mainly developed by John Robert Anderson at Carnegie Mellon University.
..... Click the link for more information.
..... Click the link for more information.
ACT-R (pronounced act-ARE: Adaptive Control of Thought--Rational) is a cognitive architecture mainly developed by John Robert Anderson at Carnegie Mellon University.
..... Click the link for more information.
..... Click the link for more information.
This article is copied from an article on Wikipedia.org - the free encyclopedia created and edited by online user community. The text was not checked or edited by anyone on our staff. Although the vast majority of the wikipedia encyclopedia articles provide accurate and timely information please do not assume the accuracy of any particular article. This article is distributed under the terms of GNU Free Documentation License.