High capacity associative memory with bipolar and binary, biased patterns
Chen, W., Adams, R.G., Calcraft, L., Davey, N. and Steuber, Volker
(2007)
High capacity associative memory with bipolar and binary, biased patterns.
The high capacity associative memory model is interesting due to its significantly higher capacity when compared with the standard Hopfield model. These networks can use either bipolar or binary patterns, which may also be biased. This paper investigates the performance of a high capacity associative memory model trained with biased patterns, using either bipolar or binary representations. Our results indicate that the binary network performs less well under low bias, but better in other situations, compared with the bipolar network.
Item Type | Article |
---|---|
Date Deposited | 27 Jul 2024 00:37 |
Last Modified | 27 Jul 2024 00:37 |
Downloads
Share this file
Explore Further
Read more research from the creator(s):
Find work associated with the faculties and division(s):