Please wait ...
0% Complete
Home
/
12th International Conference on Computer and Knowledge Engineering
GAP: Fault tolerance Improvement of Convolutional Neural Networks through GAN-aided Pruning
Authors :
Pouya Hosseinzadeh
1
Yasser Sedaghat
2
Ahad Harati
3
1- Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran
2- Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran
3- Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran
Keywords :
CNN،fault tolerance،auxiliary pruning task،generalization،GAN،N-version programming،ensemble learning،bit-flip fault
Abstract :
Functionality and accuracy degradation imposed by Bit-Flip faults (BF) on the CNNs' weights makes it vital first to evaluate neural networks' behavior in the presence of faults in the design phase and then make use of these models, especially in safety-critical applications like autonomous vehicles. In the following paper, we propose a novel approach to improve the fault tolerance of convolutional neural networks through pruning their parameters with regard to their gradients instead of the more commonly used norm values. In particular, the gradient of the network's parameters on an auxiliary classification task based on Generative Adversarial Network (GAN) is exploited to identify parameters of lower generalization. Due to the inherent efficiency that all pruning techniques introduce into the model, it is practical to use the ensembled of pruned models. In this paper, we evaluate the functionality of the naïve ensemble versus the ensemble of three differently pruned models. This idea comes from the N-version Programming (NVP) concept of dependability literature. To assess the resiliency of our model, we conduct comprehensive random bit-flip fault injection experiments. Comparing the result of our approach to ordinary pruning techniques, we show that the classification accuracy is improved by 20% in the presence of a single fault in the network. Making an NVP ensemble of three VGG-16 GAN-aided pruned networks, we make a 10% further accuracy improvement in the presence of a single random fault in each base-learner for the CIFAR-10 dataset.
Papers List
List of archived papers
Improved TrustChain for Lightweight Devices
Seyed Salar Ghazi - Haleh Amintoosi
Optimizing the controller placement problem in SDN with uncertain parameters with robust optimization
Mohammad Kazemi - AhmadReza Montazerolghaem
Density Estimation Helps Adversarial Robustness
Afsaneh Hasanebrahimi - Bahareh Kaviani Baghbaderani - Reshad Hosseini - Ahmad Kalhor
Lempel-Ziv-based Hyper-Heuristic Solution for Longest Common Subsequence Problem
Mahdi Nasrollahi - Reza Shami Tanha - Mohsen Hooshmand
A Novel Deformable Registration Method for Cerebral Magnetic Resonance Images
Bahareh Asadpour Dasht Bayaz - Mahdi Saadatmand - Fabrice Wallois
Enhancing Persian Word Sense Disambiguation with Large Language Models: Techniques and Applications
Fatemeh Zahra Arshia - Saeedeh Sadat Sadidpour
Iris Detection and Segmentation Using Deep Learning
Ali Khaki - Ali Aghagolzadeh - Bagher Rahimpour Cami
Attentional Bi-LSTM for Multivariate Time Series Forecasting on Edge Devices: A Case Study on NanoPi Neo Plus2
Navid Hajizadeh - Saeed Yazdani - Sara Ershadi-Nasab
Advancing Brain Tumor Detection via ViRCNN: A Fusion of Vision Transformers and Faster R-CNN
Mehrshad Momen-Tayefeh - S. AmirAli GH. Ghahramani - Ali Mohammad Afshin Hemmatyar
WBT-GAN:Wavelet based Generative Adversarial Network for Texture Synthesis
Sara Saberi moghadam - Reza Azmi - Maral Zarvani
more
Samin Hamayesh - Version 46.0.2