Improve accuracy in CNNs while using approximate computing methods

Mohammadreza Rafieinejad

doi:10.1007/s11227-024-06901-4

Return

Improve accuracy in CNNs while using approximate computing methods

2025-01-18

PRE

Mohammadreza Rafieinejad

Mohammadreza Binesh Marvasti *

Seyyed Amir Asghari

Kimiya Shahbakhti

DOI：10.1007/s11227-024-06901-4

Original

Original request for help

Save

Abstract

En 中文

Artificial neural networks have been one of the science's most influential and essential branches in the past decades. Neural networks have found applications in various fields including medical and pharmaceutical services, voice and speech recognition, computer vision, natural language processing, and video and image processing. Neural networks have many layers and consume much energy. Approximate computing is a promising way to reduce energy consumption in applications that can tolerate a degree of accuracy reduction. This paper proposes an effective method to prevent accuracy reduction after using approximate computing methods in the CNNs. The method exploits the k-means clustering algorithm to label pixels in the first convolutional layer. Then, using one of the existing pruning methods, different pruning amounts have been applied to all layers. The experimental results on three CNNs and four different datasets show that the accuracy of the proposed method has significantly improved (by 17%) compared to the baseline network.

Keywords:

Approximate computing

Computer vision

Convolutional neural network

Energy consumption

Machine learning

Neural network