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 units¹⁾, is not a theory in frames of behaviorism, but it preceded and influenced behaviorist school. Connectionism represents psychology's first comprehensive theory of learning²⁾. It was introduced by Herbert Spencer, William James and his student Edward Thorndike in the very beginning of the 20th century although its roots date way back.

Connectionism was then based on principles of associationism which claimed that³⁾⁴⁾:

• 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
• Complex ideas are composed and can be reduced to a set of simple ideas
• Simple ideas are sensations
• Simple additive rules are sufficient to predict complex ideas

But connectionism further expanded these assumptions by introducing ideas like distributed representations and supervised learning⁵⁾ and should not be confused with associationism.

At the very end of the 19th century Thorndike, one of most commonly mentioned connectionists and an important learning theorist, performed experiments first on chickens and later on cats and dogs to analyze how animals learn. 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 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.

To explain observed properties of learning, Thorndike introduced three laws of learning:⁶⁾

• 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 positive 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.

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 learning.

Another point of Thorndike's interest in the first two decades of 20th century was the 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”⁷⁾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.

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 mathematics⁸⁾, 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 mathematics⁹⁾, spelling and reading ¹⁰⁾, measurement of intelligence ¹¹⁾ and adult learning ¹²⁾ 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 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 behaviorism, but Thorndike's experiments also inspired gestalt psychology.

• 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
• Herbert Spencer, William James, Edward Thorndike

Medler, David A. A Brief History of Connectionism. Neural Computing Surveys, 1(2), p18-72. 1998.

TIP: Connectionism (E. Thorndike). Retrieved February 2, 2011.

Reinemeyer, E. Edward Lee Thorndike. Muskingum University. May 1999.

Zimmerman, Barry J. and Schunk, Dale H. Educational psychology: a century of contributions. Routledge, 2003.

Thorndike, E. The Contribution of Psychology to Education. The Journal of Educational Psychology, 1, 5-12. 1910.

E. L. Thorndike and R. S. Woodworth. The influence of improvement in one mental function upon the efficiency of other functions. Psychological Review, no. 8: 247-261. 1901.

Thorndike, E. Animal Intelligence. 1911.

Thorndike, E. Educational Psychology: The Psychology of Learning. New York: Teachers College Press. 1913.

Thorndike, E. The Psychology of Arithmetic. New York: Macmillan. 1922.

Thorndike, E. The Fundamentals of Learning. New York: Teachers College Press. 1932.

Thorndike, E. et al. Adult Learning. New York: Macmillan . 1928.