Abstract | ||
---|---|---|
The success of CNNs is accompanied by deep models and heavy storage costs. For compressing CNNs, we propose an efficient and robust pruning approach, cross-entropy pruning (CEP). Given a trained CNN model, connections were divided into groups in a group-wise way according to their corresponding output neurons. All connections with their cross-entropy errors below a grouping threshold were then rem... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1162/neco_a_01131 | Neural Computation |
Field | DocType | Volume |
Cross entropy,MNIST database,Pattern recognition,Convolutional neural network,Sparse model,Artificial intelligence,Mathematics,Machine learning,Pruning,Fold (higher-order function) | Journal | 30 |
Issue | ISSN | Citations |
11 | 0899-7667 | 0 |
PageRank | References | Authors |
0.34 | 4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rongxin Bao | 1 | 0 | 0.34 |
Xu Yuan | 2 | 61 | 24.92 |
Zhikui Chen | 3 | 692 | 66.76 |
Ruixin Ma | 4 | 32 | 4.71 |