D-Score: A Synapse-Inspired Approach for Filter Pruning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929496719884288 |
|---|---|
| author | Park, Doyoung Kim, Jinsoo Nam, Jina Chang, Jooyoung Park, Sang Min |
| author_facet | Park, Doyoung Kim, Jinsoo Nam, Jina Chang, Jooyoung Park, Sang Min |
| contents | This paper introduces a new aspect for determining the rank of the unimportant filters for filter pruning on convolutional neural networks (CNNs). In the human synaptic system, there are two important channels known as excitatory and inhibitory neurotransmitters that transmit a signal from a neuron to a cell. Adopting the neuroscientific perspective, we propose a synapse-inspired filter pruning method, namely Dynamic Score (D-Score). D-Score analyzes the independent importance of positive and negative weights in the filters and ranks the independent importance by assigning scores. Filters having low overall scores, and thus low impact on the accuracy of neural networks are pruned. The experimental results on CIFAR-10 and ImageNet datasets demonstrate the effectiveness of our proposed method by reducing notable amounts of FLOPs and Params without significant Acc. Drop. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_04470 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | D-Score: A Synapse-Inspired Approach for Filter Pruning Park, Doyoung Kim, Jinsoo Nam, Jina Chang, Jooyoung Park, Sang Min Neural and Evolutionary Computing Machine Learning This paper introduces a new aspect for determining the rank of the unimportant filters for filter pruning on convolutional neural networks (CNNs). In the human synaptic system, there are two important channels known as excitatory and inhibitory neurotransmitters that transmit a signal from a neuron to a cell. Adopting the neuroscientific perspective, we propose a synapse-inspired filter pruning method, namely Dynamic Score (D-Score). D-Score analyzes the independent importance of positive and negative weights in the filters and ranks the independent importance by assigning scores. Filters having low overall scores, and thus low impact on the accuracy of neural networks are pruned. The experimental results on CIFAR-10 and ImageNet datasets demonstrate the effectiveness of our proposed method by reducing notable amounts of FLOPs and Params without significant Acc. Drop. |
| title | D-Score: A Synapse-Inspired Approach for Filter Pruning |
| topic | Neural and Evolutionary Computing Machine Learning |
| url | https://arxiv.org/abs/2308.04470 |