ON THE CAPACITY OF MULTILAYER NEURAL NETWORKS TRAINED WITH BACKPROPAGATION
2000 ◽
Vol 10
(04)
◽
pp. 281-285
Keyword(s):
The capacity of a layered neural network for learning hetero-associations is studied numerically as a function of the number M of hidden neurons. We find that there is a sharp change in the learning ability of the network as the number of hetero-associations increases. This fact allows us to define a maximum capacity C for a given architecture. It is found that C grows logarithmically with M.
Keyword(s):
Keyword(s):
1989 ◽
Vol 01
(02)
◽
pp. 177-186
Keyword(s):
2008 ◽
Vol 18
(02)
◽
pp. 123-134
◽
Keyword(s):
2020 ◽
Vol 1
(2)
◽
pp. 1-9
2001 ◽
Vol 11
(01)
◽
pp. 33-42
◽
2020 ◽
2019 ◽
Vol 22
(5)
◽
pp. 52-60