0% Complete
Home
/
13th International Conference on Computer and Knowledge Engineering
Compressing Deep Neural Networks Using Explainable AI
Authors :
Kimia Soroush
1
Mohsen Raji
2
Behnam Ghavami
3
1- Shiraz university
2- Shiraz university
3- Shahid Bahonar University of Kerman
Keywords :
Deep Neural Networks،Compression،Explainable-AI
Abstract :
Abstract— Deep neural networks (DNNs) have demonstrated remarkable performance in many tasks but it often comes at a high computational cost and memory usage. Compression techniques, such as pruning and quantization, are applied to reduce the memory footprint of DNNs and make it possible to accommodate them on resource-constrained edge devices. Recently, explainable artificial intelligence (XAI) methods have been introduced with the purpose of understanding and explaining AI methods. XAI can be utilized to get to know the inner functioning of DNNs, such as the importance of different neurons and features in the overall performance of DNNs. In this paper, a novel DNN compression approach using XAI is proposed to efficiently reduce the DNN model size with negligible accuracy loss. In the proposed approach, the importance score of DNN parameters (i.e. weights) are computed using a gradient-based XAI technique called Layer-wise Relevance Propagation (LRP). Then, the scores are used to compress the DNN as follows: 1) the parameters with the negative or zero importance scores are pruned and removed from the model, 2) mixed-precision quantization is applied to quantize the weights with higher/lower score with higher/lower number of bits. The experimental results show that, the proposed compression approach reduces the model size by 64% while the accuracy is improved by 42% compared to the state-of-the-art XAI-based compression method.
Papers List
List of archived papers
Evolutionary Approach to GAN Hyperparameter Tuning: Minimizing Discriminator and Generator Loss Functions
Sajad Haghzad Klidbary - Anahita Babaei - Ramin Ghorbani
A New Time Series Approach in Churn Prediction with Discriminatory Intervals
Hedieh Ahmadi - Seyed Mohammad Hossein Hasheminejad
A Comprehensive Dataset of Real-scene Images for Text Detection and Recognition in Persian
Iman Souzanchi - Ramin Rahimi - Mohammad Ali Majidi Anvari - Atefeh Baniasadi - Ashkan Sadeghi - Mohammad Reza Mohammadi
Real-Time Vehicle Detection and Classification in UAV imagery Using Improved YOLOv5
Mohammad Hossein Hamzenejadi - Hadis Mohseni
Farsi Text in Scene: A new dataset
Ali Salmasi - Ehsanollah Kabir
SUT: a new multi-purpose synthetic dataset for Farsi document image analysis
Elham Shabaninia - Fatemeh sadat Eslami - Ali Afkari Fahandari - Hossein Nezamabadi-pour
GAP: Fault tolerance Improvement of Convolutional Neural Networks through GAN-aided Pruning
Pouya Hosseinzadeh - Yasser Sedaghat - Ahad Harati
A Novel Hybrid Method for Clustering Text Documents using Evolutionary Optimization
Muhammad Naderi - Maryam Amiri
FAHP-OF: A New Method for Load Balancing in RPL-based Internet of Things (IoT)
Mohammad Koosha - Behnam Farzaneh - Emad Alizadeh - Shahin Farzaneh
Improving Motor Imagery Classification in BCI Systems Using EMD and Multi-Layer CNNs
Reza Arghand - Ali Chaibakhsh - Moein Radman
more
Samin Hamayesh - Version 42.2.1