The authors discuss two important aspects in the multilayer feed-forward neural nets: the optimal number of hidden units per layer, and the optimal number of synaptic weights between two adjacent layers. On the basis of simulations, they conjecture that the optimal number of hidden units shall be equal to or a little bit more than M-1 for an efficient learning, where M is the number of pairs of training patterns used. Locally interconnected nets may be useful for some real applications where geometrical properties are significant. By introducing highway links into the locally interconnected nets, the convergence speed can be improved significantly.
|Original language||English (US)|
|Number of pages||4|
|Journal||ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|
|State||Published - Jan 1 1988|
All Science Journal Classification (ASJC) codes
- Signal Processing
- Electrical and Electronic Engineering