Name
Abstract | ||
|---|---|---|
Sparse coding has high-performance encoding and ability to express images, sparse encoding basis vector plays a crucial role. The computational complexity of the most existing sparse coding basis vectors of is relatively large. In order to reduce the computational complexity and save the time to train basis vectors. A new Hebbian rules based method for computation of sparse coding basis vectors is proposed in this paper. A two-layer neural network is constructed to implement the task. The main idea of our work is to learn basis vectors by removing the redundancy of all initial vectors using Hebbian rules. The experiments on natural images prove that the proposed method is effective for sparse coding basis learning. It has the smaller computational complexity compared with the previous work. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICNC.2009.624 | ICNC (1) |
Keywords | Field | DocType |
novel hebbian rule,high-performance encoding,novel hebbian rules,sparse coding,sparse coding basis learning,sparse encoding basis vector,sparse coding basis vectors,smaller computational complexity,hebbian rule,basis vector,sparse coding basis vector,computational complexity,existing sparse,neural nets,hebbian learning,redundancy,encoding,neural network,rule based,basis function,vectors,sparse matrices | Pattern recognition,Neural coding,Computer science,Sparse approximation,Hebbian theory,Basis function,Artificial intelligence,Artificial neural network,Basis (linear algebra),Machine learning,Sparse matrix,Computational complexity theory | Conference |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Baixian Zou | 1 | 6 | 1.88 |
| Jun Miao | 2 | 220 | 22.17 |
| Xiaoling Yang | 3 | 0 | 0.34 |
| Lijuan Duan | 4 | 215 | 26.13 |
| Yuanhua Qiao | 5 | 31 | 6.68 |