Logo image
Automatic Deep Compression Based on Simplified Swarm Optimization
Conference paper

Automatic Deep Compression Based on Simplified Swarm Optimization

Yuh Herng Choke and Wei-Chang Yeh
2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023 - Proceedings, pp.807-808
2023

Abstract

Convolutional Neural Network Model Pruning Simplifies Swarm Optimization Artificial Intelligence Human-Computer Interaction Information Systems Information Systems and Management Electrical and Electronic Engineering Media Technology Instrumentation
In recent years, convolutional neural networks (CNNs) have been proven and widely applied in the field of image recognition, including anomaly detection in manufacturing sites, and object detection in autonomous driving. However, the parameters obtained from the CNN increase exponentially with the depth of the network. Therefore, it is difficult to deploy the model in environments with limited computing resources. This study proposes a compression method for CNN by combining Simplified Swarm Optimization(SSO) with structured pruning. Our method can compress VGG16 to approximately 8.3 times smaller without sacrificing accuracy. The more important is, our method uses a heuristic approach to find the optimal pruning scheme without the need for repeated experimental verification.

Metrics

1 Record Views

Details

Logo image