Abstract
This paper presents a theory and methodology on training of artificial neural networks in a general setting.
Starting with defining general concepts, and analyzing associated properties of artificial neural networks, this paper formalizes, categorizes, and characterizes artificial neural networks from a system point of view. This paper focuses on the analysis aspect of artificial neural nets to address and investigate trainability and representability; on the synthesis aspect of artificial neural nets to provide design principles to the systems; and on the algorithmic aspect of the artificial neural nets to develop effective and efficient learning paradigm, etc.
Starting with defining general concepts, and analyzing associated properties of artificial neural networks, this paper formalizes, categorizes, and characterizes artificial neural networks from a system point of view. This paper focuses on the analysis aspect of artificial neural nets to address and investigate trainability and representability; on the synthesis aspect of artificial neural nets to provide design principles to the systems; and on the algorithmic aspect of the artificial neural nets to develop effective and efficient learning paradigm, etc.
| Original language | English |
|---|---|
| Title of host publication | International 1989 Joint Conference on Neural Networks |
| Publisher | IEEE |
| Pages | 387-393 |
| Volume | 2 |
| DOIs | |
| Publication status | Published - Jun 1989 |
| Externally published | Yes |
| Event | 1989 International Joint Conference on Neural Networks - Washington, United States Duration: 18 Jun 1989 → 22 Jun 1989 |
Conference
| Conference | 1989 International Joint Conference on Neural Networks |
|---|---|
| Country/Territory | United States |
| City | Washington |
| Period | 18/06/89 → 22/06/89 |