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
Optimizing Question-Answering Framework Through Integration of Text Summarization Model and Third-Generation Generative Pre-Trained Transformer
Ervin Gubin Moung - Toh Sin Tong - Maisarah Mohd Sufian - Valentino Liaw - Ali Farzamnia - Farashazillah Yahya
Novel Insights in Deep Learning for Predicting Climate Phenomena
Mohammad Naisipour - Saghar Ganji - Iraj Saeedpanah - Behnam Mehrakizadeh - Ahmad Reza Labibzadeh
Enhancing Vehicle Make and Model Recognition with 3D Attention Modules
Narges Semiromizadeh - Omid Nejati Manzari - Shahriar B. Shokouhi - Sattar Mirzakuchaki
Sensitivity Reliability Analysis of Power Distribution Networks Using Fuzzy Logic
Mohammed Wadi - Wisam Elmasry - Ismail Kucuk - Hossein Shahinzadeh
Semi-automatic Detection of Persian Stopwords using FastText Library
Mohammad Dehghani - Mohammad Manthouri
An interactive user groups recommender system based on reinforcement learning
Hediyeh Naderi Allaf - Mohsen Kahani
AL-YOLO: Accurate and Lightweight Vehicle and Pedestrian Detector in Foggy Weather
Behdad Sadeghian Pour - Hamidreza Mohammadi Jozani - Shahriar Baradaran Shokouhi
Enhanced Autoencoder-based Clustering for Message Analysis in Binary Protocols
Mohaddese Nemati - Shiva Mahmoudzadeh - Mehdi Teimouri
An Attention-Based Model for Clinical Time Series Prediction: Enhancing ICU Readmission Prediction
Hananeh Sadat Madinei - Mohammad Reza Keyvanpour - Seyed Vahab Shojaedini
A scalable blockchain-based educational network for data storage and assessment
Maryam Fattahi Vanani - Hamidreza Shayegh Borujeni - Ali Nourollah
more
Samin Hamayesh - Version 41.7.6