Abstract
The problem of which functions can be computed by a neural network is considered. The answers to this question determine the capabilities and limitations of a neural network as a general-purpose computer. A computation process is defined as the dynamic motion of input states to output states. Several types of deterministic neural network models are compared with the classical computational model of the Turing machine, and their computational capabilities are determined.
Original language | English |
---|---|
Pages | 535-540 |
Number of pages | 6 |
DOIs | |
State | Published - 1990 |
Event | 1990 International Joint Conference on Neural Networks - IJCNN 90 Part 3 (of 3) - San Diego, CA, USA Duration: 17 Jun 1990 → 21 Jun 1990 |
Conference
Conference | 1990 International Joint Conference on Neural Networks - IJCNN 90 Part 3 (of 3) |
---|---|
City | San Diego, CA, USA |
Period | 17/06/90 → 21/06/90 |