Learning of associative memory networks based upon cone-like domains of attraction
✍ Scribed by Koichi Niijima
- Book ID
- 104348758
- Publisher
- Elsevier Science
- Year
- 1997
- Tongue
- English
- Weight
- 673 KB
- Volume
- 10
- Category
- Article
- ISSN
- 0893-6080
No coin nor oath required. For personal study only.
✦ Synopsis
A learning algorithm for single layer perceptrons is proposed. First, a cone-like domain is derived such that all its elements can be recognized as a stored pattern in the perceptron network. The learning algorithm is obtained as a process that enlarges the cone-like domain. For autoassociative networks, it is shown that the cone-like domain becomes a domain of attraction for a storedpattern in the network. In this case, extended domains of attraction are also obtained by feeding the outputs of the network back to the input layer In computer simulations, character recognition ability of the autoassociative network is examined.