learning_theories:connectionism
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
|
learning_theories:connectionism [2011/02/18 13:29] jpetrovic [What is connectionism?] |
learning_theories:connectionism [2011/04/08 11:24] jpetrovic [Bibliography] |
||
|---|---|---|---|
| Line 4: | Line 4: | ||
| ===== General ===== | ===== General ===== | ||
| - | Connectionism, today defined as an approach in the fields of artificial intelligence, cognitive psychology, cognitive science and philosophy of mind which **models mental** or **behavioral phenomena** with **networks of simple units**(([[http://www.wordiq.com/definition/Connectionism|wordiQ: Connectionism - Definition]])), is not a theory in frames of [[learning_paradigms:behaviorism]], it **preceded** and **influenced behaviorist school**. Although it is today used in different contexts (mostly referring to neural networks and artificial neural networks that have not emerged until second half of the 20th century) it has origins dating as far back as Greek philosopher Aristotele, who claimed that memory is composed of simple elements connected in a variety of ways((J. A. Anderson, A. Pellionisz and Rosenfeld, E. Neurocomputing 2. MIT Press, Cambridge, MA, 1990.)). | + | Connectionism, today defined as an approach in the fields of artificial intelligence, cognitive psychology, cognitive science and philosophy of mind which **models mental** or **behavioral phenomena** with **networks of simple units**(([[http://www.wordiq.com/definition/Connectionism|wordiQ: Connectionism - Definition]])), is not a theory in frames of [[learning_paradigms:behaviorism]], it **preceded** and **influenced behaviorist school**. Although it is today used in different contexts (mostly referring to neural networks and artificial neural networks that have not emerged until second half of the 20th century) it has origins dating as far back as Greek philosopher Aristotele, who claimed that memory is composed of simple elements connected in a variety of ways(([[http://books.google.hr/books?id=u6j6HTS-rVQC&pg=PA47&dq=J.+A.+Anderson,+A.+Pellionisz+and+Rosenfeld,+E.+Neurocomputing+2&hl=hr&ei=G6drTezgJMO58gPTv-nyBw&sa=X&oi=book_result&ct=result&resnum=1&ved=0CCkQ6AEwAA#v=onepage&q&f=false|J. A. Anderson, A. Pellionisz and Rosenfeld, E. Neurocomputing 2. MIT Press, Cambridge, MA, 1990.]])). |
| Line 10: | Line 10: | ||
| ===== What is connectionism? ===== | ===== What is connectionism? ===== | ||
| - | Connectionism represents psychology's first comprehensive theory of learning((Zimmerman, Barry J., and Dale H. Schunk. Educational psychology: a century of contributions. Routledge, 2003.)). It was later introduced by [[http://www.mnsu.edu/emuseum/information/biography/pqrst/spencer_herbert.html|Herbert Spencer]], [[http://plato.stanford.edu/entries/james/|William James]] and his student [[http://www.muskingum.edu/~psych/psycweb/history/thorndike.htm|Edward Thorndike]] in the very beginning of the 20th century. Connectionism was then **based on principles of associationism** which claimed that((W. Bechtel and Abrahamsen, A. Connectionism and the Mind: An Introduction to Parallel Processing in Networks. Blackwell, Cambridge, MA, 1991.)): | + | Connectionism represents psychology's first comprehensive theory of learning(([[http://books.google.hr/books?id=bqo5A2nBwHYC&printsec=frontcover#v=onepage&q&f=false|Zimmerman, Barry J., and Dale H. Schunk. Educational psychology: a century of contributions. Routledge, 2003.]])). It was introduced by [[http://www.mnsu.edu/emuseum/information/biography/pqrst/spencer_herbert.html|Herbert Spencer]], [[http://plato.stanford.edu/entries/james/|William James]] and his student [[http://www.muskingum.edu/~psych/psycweb/history/thorndike.htm|Edward Thorndike]] in the very beginning of the 20th century. Connectionism was then **based on principles of associationism** which claimed that(([[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.86.7504&rep=rep1&type=pdf|Medler, David A. A Brief History of Connectionism. Neural Computing Surveys, 1(2), p18-72. 1998.]]))(([[http://books.google.hr/books?id=wFqlQgAACAAJ&dq=Connectionism+and+the+Mind:+An+Introduction+to+Parallel+Processing+in+Networks&hl=hr&ei=kKdrTdv3C5Sq8QPzs8W_BQ&sa=X&oi=book_result&ct=result&resnum=1&ved=0CCcQ6AEwAA|W. Bechtel and Abrahamsen, A. Connectionism and the Mind: An Introduction to Parallel Processing in Networks. Blackwell, Cambridge, MA, 1991.]])): |
| - | * Mental elements or ideas become associated with one another through experience | + | * //Mental elements or ideas become associated with one another through experience// |
| - | * Experience consists of such things as spatial and temporal contiguity and (dis)similarity of ideas | + | * //Experience consists of such things as spatial and temporal contiguity and (dis)similarity of ideas// |
| - | * Complex ideas are composed and can be reduced to a set of simple ideas | + | * //Complex ideas are composed and can be reduced to a set of simple ideas// |
| - | * Simple ideas are sensations | + | * //Simple ideas are sensations// |
| - | * Simple additive rules are sufficient to predict complex ideas | + | * //Simple additive rules are sufficient to predict complex ideas// |
| - | But connectionism **expands** this **ideas of associationism** by introducing distributed representations or supervised learning(([[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.86.7504&rep=rep1&type=pdf|Medler, David A. A Brief History of Connectionism. Neural Computing Surveys, 1(2), p18-72. 1998.]])) and should not be confused with associationism. Although he is considered one of the first true connectionist, William James' student Edward Thorndike also made the move towards behaviorist ideas. | + | But connectionism **expands** this **ideas of associationism** by introducing ideas like [[:glossary#distributed_representations|distributed representations]] or supervised learning(([[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.86.7504&rep=rep1&type=pdf|Medler, David A. A Brief History of Connectionism. Neural Computing Surveys, 1(2), p18-72. 1998.]])) and should not be confused with associationism. |
| - | At the very end of 19th century Thorndike performed experiments first on chickens and later on cats and dogs. In one experiment he placed a hungry cat inside a //puzzle box//, which had a mechanism that would open the doors of the box every time a string would be pulled or a button pushed. Behavior which resulted in opening the doors was slowly increased as the cat after each successful attempt to open the door needed a bit less time repeat the same action after being put back into the box. Based on this experiment Thorndike concluded learning is **incremental** and **not insightful**, since it occurred only through forming of associations between situation and response, where correct response was achieved through repetition of trial and error. Established connections or knowledge, according to Thorndike also cause and determine intelligence. | + | [[http://historyofpsych.blogspot.com/2010/01/american-behaviorism.html|{{ images:thorndikes_cat.jpg|Thorndike's cat experiment. Image borrowed from: History of Psychology: American Behaviorism. Click on the picture to follow the link. }}]] |
| - | To explain observed properties of learning, Thorndike introduced three laws of learning. The first law is the **//law of exercise or use or frequency//**, which states that **stimulus-response** (S-R) **associations** are **strengthened through repetition** or weakened through lack of repetition. His second law, **//law of effect//**, states that the consequence or **outcome** of a situation-response event **can strengthen or weaken** the **connection** between situation and response. If an event is followed by a reinforcing stimulus, the connection will be strengthened and vice versa. The third law, **//law of readiness//**, which claims learning is facilitated by learner's readiness (emotional and motivational) to learn. This potential to learn leads to frustration if not satisfied. | + | At the very end of 19th century Thorndike performed experiments first on chickens and later on cats and dogs. In one experiment he placed a hungry cat inside a //puzzle box//, which had a mechanism that would open the doors of the box every time a string would be pulled or a button pushed. After each successful escape out of the box by opening its doors, the cat needed a bit less time to repeat the required process next time. The desired behavior slowly increased. Based on this experiment Thorndike concluded that learning is **incremental** and **not [[:glossary#insightful_learning|insightful]]**, since the learning of the correct response occurred only through repetition //trial and error// forming of associations between situation and response. Established connections or knowledge, according to Thorndike also cause and determine intelligence. |
| - | Thorndike later changed some of his views admitting that he was wrong and that negative reinforcement (punishment) does not really lead to any kind of learning. This had great influence on educational process helping to end the practice of punishing the students for incorrect answers. This laws have set the **basic principles** of **behaviorist stimulus-response** views on **learning**. | + | To explain observed properties of learning, Thorndike introduced three laws of learning. |
| - | Another point of Thorndike's interest in the first two decades of 20th century was the **knowledge transfer** in terms of generalizing the knowledge or skills and applying them for another problem. Thorndike performed experimental studies by which he showed knowledge transfer is specific rather then general and will not occur unless learned problem and given problem share many characteristics. This was the opposite of what school systems mostly suggested at the time, that some school subjects improve student's mind in general (//doctorine of formal discipline//). | + | * **//Law of exercise//** (also referred to //as law of use// or //law of frequency//), which states that **stimulus-response** (S-R) **associations** are **strengthened through repetition** or weakened through lack of repetition. |
| + | * **//Law of effect//** which states that the consequence or **outcome** of a situation-response event **can strengthen or weaken** the **connection** between situation and response. If an event is followed by a reinforcing stimulus, the connection will be strengthened and vice versa. | ||
| + | * **//Law of readiness//** which claims learning is facilitated by learner's readiness (emotional and motivational) to learn. This potential to learn leads to frustration if not satisfied. | ||
| - | In his book on learning of mathematics((Thorndike, E. The Psychology of Arithmetic. New York: Macmillan. 1922.)), Thorndike suggested problems children are expected to solve and learn from should be realistic. He also emphasizes importance of **repetition** and insists on repetitive practice of basic arithmetic operations. Some of the principles in this book even seem inconsistent with his views on learning: here he refers to learning as meaningful and insightful. Well-learned basic skills enable learning of higher-order skills. | + | Thorndike later changed some of his views admitting that he was wrong and that negative reinforcement (punishment) does not really lead to any kind of learning. This had great influence on educational process helping to end the practice of punishing the students for incorrect answers. This laws have set the **basic principles** of **behaviorist stimulus-response** views on **learning**. |
| - | Thorndike is also credited for introduction and standardization of a number of tests of knowledge and intelligence (CAVD). In his own words, //whatever exists at all exists in some amount.//((Thorndike, Edward L. Individual differences. Psychological bulletin. 1918.)) | + | Another point of Thorndike's interest in the first two decades of 20th century was the **[[:glossary#transfer|transfer of practice]]**, later often referred to as //transfer of learning//. Idea of transfer of practice is to generalize the knowledge or skills and apply them for another problem. Thorndike performed experimental studies showing that transfer of learning will not occur unless learned problem and given problem have many common characteristics. This was the opposite of what school systems mostly suggested at the time: that some school subjects like Latin language and mathematics improve student's mind in general (//doctrine of formal discipline//). |
| + | Guided by the principle that "//whatever exists at all exists in some amount//"((Thorndike, Edward L. Individual differences. Psychological bulletin. 1918.))Thorndike has introduced a number of tests of knowledge and intelligence. His //CAVD// (completion, arithmetic, vocabulary and directions) test set the major principles and standards of modern intelligence tests. | ||
| ===== What is the practical meaning of connectivism? ===== | ===== What is the practical meaning of connectivism? ===== | ||
| - | Connectionism was at its time considered a general theory of learning for both humans and animals. Thorndike's ideas which could well be applied for learning are the idea that rewards promote learning and that repetition enhances learning. For example, learning to multiply by three should be learned in context of converting feet to yards. | + | Connectionism was at its time considered a general theory of learning for both humans and animals. Thorndike's ideas which could well be applied for learning are the idea that rewards promote learning and that repetition enhances learning. |
| - | + | ||
| + | In his book on learning of mathematics((Thorndike, E. The Psychology of Arithmetic. New York: Macmillan. 1922.)), Thorndike suggested problems children are expected to solve and learn from should be realistic. For example learning to multiply by three should be learned in context of converting feet to yards. He also emphasizes importance of **repetition** and insists on repetitive practice of basic arithmetic operations. Some of the principles in this book even seem inconsistent with his views on learning: here he refers to learning as meaningful and insightful. Well-learned basic skills enable learning of higher-order skills. | ||
| + | |||
| + | Thorndike tried to apply this to learning **mathematics**((Thorndike, E. The Psychology of Arithmetic. New York: Macmillan. 1922.)), **spelling and reading** ((Thorndike, E. The Teacher's Word Book. New York: Teachers College. 1921.)), measurement of **intelligence** ((Thorndike, E. at al. The Measurement of Intelligence. New York: Teachers College Press. 1927.)) and adult learning ((Thorndike, E. et al. Adult Learning. New York: Macmillan. 1928. )) mostly through his laws of learning. He was one of the pioneers of **active learning**, proposing children should learn by themselves rather than being thought. | ||
| - | Thorndike tried to apply this to learning **mathematics**((Thorndike, E. The Psychology of Arithmetic. New York: Macmillan. 1922.)), **spelling and reading** ((Thorndike, E. The Teacher's Word Book. New York: Teachers College. 1921.)), measurement of **intelligence** ((Thorndike, E. at al. The Measurement of Intelligence. New York: Teachers College Press. 1927.)) and adult learning ((Thorndike, E. et al. Adult Learning. New York: Macmillan. 1928. )) mostly through his laws of learning. Thorndike was one of the pioneers of **active learning**, proposing children should learn by themselves rather than being thought. | ||
| - | ===== Keywords and most important names ===== | ||
| - | * **Connectionism**, **stimulus-response**, **S-R**, **networks of simple units**, **associationism**, **supervised learning**, **law of exercise or use or frequency**, **law of effect**, **incremental learning**, **“trial and error** | ||
| - | * [[http://www.mnsu.edu/emuseum/information/biography/pqrst/spencer_herbert.html|Herbert Spencer]], [[http://plato.stanford.edu/entries/james/|William James]], [[http://www.muskingum.edu/~psych/psycweb/history/thorndike.htm|Edward Thorndike]] | ||
| ===== Criticisms ===== | ===== Criticisms ===== | ||
| Thorndike tried to prove that all forms of thoughts and behaviors can be explained through S-R relations with use of repetition and reward, without need for introducing any unobservable internal states, yet this is **today** generally **considered incorrect**. This //learning through response// was later in 20th century replaced by //learning as knowledge construction//. Connectionism was in the first decades of 20th century succeeded by [[learning_paradigms:behaviorism]], but Thorndike's experiments also inspired [[learning_theories:gestalt_psychology|gestalt psychology]]. | Thorndike tried to prove that all forms of thoughts and behaviors can be explained through S-R relations with use of repetition and reward, without need for introducing any unobservable internal states, yet this is **today** generally **considered incorrect**. This //learning through response// was later in 20th century replaced by //learning as knowledge construction//. Connectionism was in the first decades of 20th century succeeded by [[learning_paradigms:behaviorism]], but Thorndike's experiments also inspired [[learning_theories:gestalt_psychology|gestalt psychology]]. | ||
| + | |||
| + | |||
| + | ===== Keywords and most important names ===== | ||
| + | |||
| + | * **Connectionism**, **stimulus-response**, **S-R**, **networks of simple units**, **associationism**, **supervised learning**, **law of exercise or use or frequency**, **law of effect**, **incremental learning**, **trial and error** | ||
| + | * [[http://www.mnsu.edu/emuseum/information/biography/pqrst/spencer_herbert.html|Herbert Spencer]], [[http://plato.stanford.edu/entries/james/|William James]], [[http://www.muskingum.edu/~psych/psycweb/history/thorndike.htm|Edward Thorndike]] | ||
| Line 51: | Line 59: | ||
| [[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.86.7504&rep=rep1&type=pdf|Medler, David A. A Brief History of Connectionism. Neural Computing Surveys, 1(2), p18-72. 1998.]] | [[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.86.7504&rep=rep1&type=pdf|Medler, David A. A Brief History of Connectionism. Neural Computing Surveys, 1(2), p18-72. 1998.]] | ||
| - | [[http://tip.psychology.org/thorn.html|TIP: Connectionism (E. Thorndike).]] | + | [[http://tip.psychology.org/thorn.html|TIP: Connectionism (E. Thorndike).]] Retrieved February 2, 2011. |
| [[http://www.muskingum.edu/~psych/psycweb/history/thorndike.htm|Reinemeyer, E. Edward Lee Thorndike. Muskingum University. May 1999.]] | [[http://www.muskingum.edu/~psych/psycweb/history/thorndike.htm|Reinemeyer, E. Edward Lee Thorndike. Muskingum University. May 1999.]] | ||
| - | [[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.86.7504&rep=rep1&type=pdf|Medler, David A. A Brief History of Connectionism. Neural Computing Surveys, 1(2), p18-72. 1998.]] | + | [[http://books.google.hr/books?id=bqo5A2nBwHYC&printsec=frontcover&dq=Educational+psychology:+a+century+of+contributions&hl=hr&ei=PdSeTfApztvjBpyHtYcD&sa=X&oi=book_result&ct=result&resnum=1&ved=0CCcQ6AEwAA#v=onepage&q&f=false|Zimmerman, Barry J. and Schunk, Dale H. Educational psychology: a century of contributions. Routledge, 2003.]] |
| - | + | ||
| - | Zimmerman, Barry J. and Schunk, Dale H. Educational psychology: a century of contributions. Routledge, 2003. | + | |
| ===== Read more ===== | ===== Read more ===== | ||
| Line 64: | Line 70: | ||
| [[http://psychclassics.yorku.ca/Thorndike/Animal/index.htm|Thorndike, E. Animal Intelligence. 1911.]] | [[http://psychclassics.yorku.ca/Thorndike/Animal/index.htm|Thorndike, E. Animal Intelligence. 1911.]] | ||
| + | |||
| + | [[http://www.google.com/books?hl=hr&lr=&id=QYlJzBjl4-kC&oi=fnd&pg=PR5&dq=Connectionism+and+the+Mind:+An+Introduction+to+Parallel+Processing+in+Networks.&ots=cWFkwwysIw&sig=bnAdzYQBCWRru2D7I_i3b0TilUc#v=onepage&q=Connectionism%20and%20the%20Mind%3A%20An%20Introduction%20to%20Parallel%20Processing%20in%20Networks.&f=false|Bechtel, William, and Adele A. Abrahamsen. Connectionism and the mind: parallel processing, dynamics, and evolution in networks. Wiley-Blackwell, 2002.]] | ||
| + | |||
| Thorndike, E. Educational Psychology: The Psychology of Learning. New York: Teachers College Press. 1913. | Thorndike, E. Educational Psychology: The Psychology of Learning. New York: Teachers College Press. 1913. | ||
learning_theories/connectionism.txt · Last modified: 2023/06/19 18:03 (external edit)
Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 4.0 International
