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
Data Clustering using Chimp Optimization Algorithm
SAYED PEDRAM HAERI BOROUJENI - ELNAZ PASHAEI
A 2D-CNN Architecture for Improving the Classification Accuracy of an Electronic Nose with Different Sensor Positions
Hannaneh Mahdavi - Reza Goldoust - Saeideh Rahbarpour
Impossible differential and zero-correlatin linear cryptanalysis of Marx, Marx2, Chaskey andSpeck32
Mahshid Saberi - Nasour Bagheri - Sadegh Sadeghi
Joint ADC-less Analog Demodulator and Decoder for Extended Binary (8, 4, 4) Hamming Channel Code
Mir Mahdi Safari - Jafar Pourrostam - Behzad Mozaffari Tazehkand
A Novel Deformable Registration Method for Cerebral Magnetic Resonance Images
Bahareh Asadpour Dasht Bayaz - Mahdi Saadatmand - Fabrice Wallois
Analysis of Insect-plant Interactions Affected by Mining operations, A Graph Mining Approach
Mohammad Heydari - Ali Bayat - Amir Albadvi
EfficientNetB0’s Hybrid Approach for Brain Tumor Classification from MRI Images Using Deep Learning and Bagging Trees
Yeganeh Modaresnia - Farhad Abedinzadeh Torghabeh - Seyyed Abed Hosseini
A Novel Approach for Image-Text Matching Cross-Modal Space Learning
Amirreza Ebrahimi - Mohammad Javad Parseh - Pejman Rasti
Stock market prediction using multi-objective optimization
Mahshid Zolfaghari - Hamid Fadishei - Mohsen Tajgardan - Reza Khoshkangini
Sensitivity Reliability Analysis of Power Distribution Networks Using Fuzzy Logic
Mohammed Wadi - Wisam Elmasry - Ismail Kucuk - Hossein Shahinzadeh
more
Samin Hamayesh - Version 41.3.1