What is connectionism, and how does it contrast with GOFAI?
Connectionism was proposed by Donald Hebb in 1940s and is used in the studies of artificial intelligence. It is a set of approach, also utilized in other disciplines like cognitive psychology, neuroscience, and psychology. It models behavioral phenomena by interconnecting networks of simple units.
GOFAI (Good Old-Fashioned Artificial Intelligence), also called symbolic artificial intelligence, is a collective term for all methods used in artificial intelligence research based on symbolic coding of problems and search. John Haughland termed GOFAI in 1985.
Connectionism and GOFAI differ from each other and their differences are tabulated below.
| CONNECTIONISM | GOFAI |
| Connectionism works by analyzing the codes delivered by interconnected networks of small units. It mostly represents neuron system in human brain. | In GOFAI, the symbols are provided to each human behavior, which is being studied for the analytical purposes. |
| It is slightly a slower process in terms of processing and analyzing data. | It is a slightly faster process than connectionism. |
| In connectionism, the process can perform several tasks at one go. | GOFAI can synthesize the information they contain. |
| There is unpredictability in processing pragmatic problems with connectionism. The solutions provided by this mechanism may be empirically correct but not in accordance with researchers. | GOFAI works on symbols, and hence, do not provide such ambiguities. |
| Connectionism can handle simpler problems more efficiently. | GOFAI work excellently in solving simpler cases, but it is still not efficient for complex data. |