Fuzzy Pruning for Compression of Convolutional Neural Networks
| Autor: | Yue Li, Wei Bin Zhao, Lin Shang |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Fuzzy set 020206 networking & telecommunications Pattern recognition 02 engineering and technology Filter (signal processing) 010501 environmental sciences 01 natural sciences Convolutional neural network Fuzzy logic Set (abstract data type) Compression (functional analysis) 0202 electrical engineering electronic engineering information engineering Artificial intelligence Pruning (decision trees) business Computer Science::Databases Membership function 0105 earth and related environmental sciences |
| Zdroj: | FUZZ-IEEE |
| Popis: | Pruning can be used in Convolutional Neural Networks(CNNs) to reduce the consumption of computations. In the iteration of pruning, a fixed ratio of filters or weights are pruned after evaluating their importance according to a certain criterion, which has the risk of leading to mis-pruning when the distribution of the importance is imbalanced. We propose a strategy to assist pruning for CNNs at filter level. Firstly, in order to evaluate importance and non-importance about filters in the network, we design two fuzzy membership functions respectively, then we evaluate all filters by their membership function value, finally, α-cut set is employed to determine the ones to be pruned . Experimental results demonstrate the effectiveness of our strategy, since it can obtain more compression than the popular pruning algorithms at similar accuracy level. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|