0% Complete
Home
/
13th International Conference on Computer and Knowledge Engineering
Pruning and Mixed Precision Techniques for Accelerating Neural Network
Authors :
Mahsa Zahedi
1
Mohammad Sediq Abazari Bozhgani
2
Abdorreza Savadi
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 :
Prune،Mixed Precision،Neural Network،Machine Learning،image processing
Abstract :
This study investigates the use of pruning and mixed precision techniques to enhance neural network performance, focusing on the AlexNet model trained on the MNIST dataset. Pruning removes unnecessary components, while mixed precision optimizes memory and computation efficiency. The study applies structured pruning to create a pruned model, which achieves improved inference time compared to the baseline. Automatic mixed precision is also employed, further enhancing inference speed. Combining pruning and mixed precision in a single model yields superior performance, surpassing the individual approaches. The combined model achieves significantly faster inference time by leveraging both techniques. The research highlights the potential of combining pruning and mixed precision for faster and more efficient neural network computations, reducing network size, optimizing memory utilization, and accelerating computations. The findings provide valuable insights for integrating these techniques into the AlexNet model and lay the groundwork for future exploration in larger and more complex models. This work holds promise for developing faster and more efficient deep learning models to meet the demands of real-world applications, particularly in resource-constrained environments
Papers List
List of archived papers
Iris Detection and Segmentation Using Deep Learning
Ali Khaki - Ali Aghagolzadeh - Bagher Rahimpour Cami
Improving ADHD Detection with Cost-Sensitive LightGBM
Behnam Yousefimehr - Mehdi Ghatee - Ali Heydari
A Federated Learning-Based Hybrid Deep Learning Framework for Enhanced Human Activity Recognition
Jamileh Azmoudeh - Sajjad Arghaee - Parisa Valizadeh - Samaneh Dandani - Iman Havangi - Mohammad Hossein Yaghmaee
Soccer Video Event Detection Using Metric Learning
Ali Karimi - Ramin Toosi - Mohammad Ali Akhaee
Disturbance Rejection in Quadruple-Tank System by Proposing New Method in Reinforcement Learning
Alireza Nezamzadeh - Mohammadreza Esmaeilidehkordi
SingAll: Scalable Control Flow Checking for Multi-Process Embedded Systems
Mehdi Amininasab - Ahmad Patooghy - Mahdi Fazeli
WBT-GAN:Wavelet based Generative Adversarial Network for Texture Synthesis
Sara Saberi moghadam - Reza Azmi - Maral Zarvani
Low-Cost and Hardware Efficient Implementation of Pooling Layers for Stochastic CNN Accelerators
Mobin Vaziri - Hadi Jahanirad
Adaptive-A-GCRNN: Enhancing Real-time Multi-band Spectrum Prediction through Attention-based Spatial-Temporal Modeling
Seyed majid Hosseini - Seyedeh Mozhgan Rahmatinia - Seyed Amin Hosseini Seno - Hadi Sadoghi yazdi
Designing an IT2 Fuzzy Rule-based System for Emotion Recognition Using Biological Data
Mahsa Keshtkar - Hooman Tahayori
more
Samin Hamayesh - Version 41.3.1