An iterative incremental learning algorithm for complex-valued hopfield associative memory
This paper discusses a complex-valued Hopfield associative memory with an iterative incremental learning algorithm. The mathematical proofs derive that the weight matrix is approximated as a weight matrix by the complex-valued pseudo inverse algorithm. Furthermore, the minimum number of iteratio...
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2016
|
| Subjects: | |
| Online Access: | http://eprints.um.edu.my/16812/1/99500051.pdf |
| _version_ | 1796947117628981248 |
|---|---|
| author | Masuyama, N. Chu, K.L. |
| author_facet | Masuyama, N. Chu, K.L. |
| author_sort | Masuyama, N. |
| collection | UM |
| description | This paper discusses a complex-valued Hopfield associative
memory with an iterative incremental learning algorithm. The mathematical
proofs derive that the weight matrix is approximated as a weight
matrix by the complex-valued pseudo inverse algorithm. Furthermore,
the minimum number of iterations for the learning sequence is defined
with maintaining the network stability. From the result of simulation
experiment in terms of memory capacity and noise tolerance, the proposed
model has the superior ability than the model with a complexvalued
pseudo inverse learning algorithm. |
| first_indexed | 2024-03-06T05:42:03Z |
| format | Conference or Workshop Item |
| id | um.eprints-16812 |
| institution | Universiti Malaya |
| language | English |
| last_indexed | 2024-03-06T05:42:03Z |
| publishDate | 2016 |
| record_format | dspace |
| spelling | um.eprints-168122017-01-17T07:01:17Z http://eprints.um.edu.my/16812/ An iterative incremental learning algorithm for complex-valued hopfield associative memory Masuyama, N. Chu, K.L. QA75 Electronic computers. Computer science This paper discusses a complex-valued Hopfield associative memory with an iterative incremental learning algorithm. The mathematical proofs derive that the weight matrix is approximated as a weight matrix by the complex-valued pseudo inverse algorithm. Furthermore, the minimum number of iterations for the learning sequence is defined with maintaining the network stability. From the result of simulation experiment in terms of memory capacity and noise tolerance, the proposed model has the superior ability than the model with a complexvalued pseudo inverse learning algorithm. 2016 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.um.edu.my/16812/1/99500051.pdf Masuyama, N. and Chu, K.L. (2016) An iterative incremental learning algorithm for complex-valued hopfield associative memory. In: The 23rd International Conference on Neural Information Processing (ICONIP 2016), 17 - 21 October 2016, Kyoto, Japan. |
| spellingShingle | QA75 Electronic computers. Computer science Masuyama, N. Chu, K.L. An iterative incremental learning algorithm for complex-valued hopfield associative memory |
| title | An iterative incremental learning algorithm for complex-valued hopfield associative memory |
| title_full | An iterative incremental learning algorithm for complex-valued hopfield associative memory |
| title_fullStr | An iterative incremental learning algorithm for complex-valued hopfield associative memory |
| title_full_unstemmed | An iterative incremental learning algorithm for complex-valued hopfield associative memory |
| title_short | An iterative incremental learning algorithm for complex-valued hopfield associative memory |
| title_sort | iterative incremental learning algorithm for complex valued hopfield associative memory |
| topic | QA75 Electronic computers. Computer science |
| url | http://eprints.um.edu.my/16812/1/99500051.pdf |
| work_keys_str_mv | AT masuyaman aniterativeincrementallearningalgorithmforcomplexvaluedhopfieldassociativememory AT chukl aniterativeincrementallearningalgorithmforcomplexvaluedhopfieldassociativememory AT masuyaman iterativeincrementallearningalgorithmforcomplexvaluedhopfieldassociativememory AT chukl iterativeincrementallearningalgorithmforcomplexvaluedhopfieldassociativememory |