Quantisation and Pruning for Neural Network Compression and Regularisation
Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices. In this paper, we investigate reducing the computational and memory requirements of neural networks through network pruning and quantisation. We examine their efficacy on large networks like AlexNet compared to recent compact architectures: ShuffleNet and MobileNet. Our results show that pruning and quantisation compresses these networks to less than half their original size and improves their efficiency, particularly on MobileNet with a 7x speedup. We also demonstrate that pruning, in addition to reducing the number of parameters in a network, can aid in the correction of overfitting.
Code (1)
Tasks
Network PruningNeural Network CompressionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Weight Fixing Networks
Modern iterations of deep learning models contain millions (billions) of unique parameters, each represented by a b-bit number. Popular attempts at compressing neural networks (such as pruning and quantisation) have show…
An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2
This study examines quantisation and pruning strategies to reduce energy consumption in code Large Language Models (LLMs) inference. Using StarCoder2, we observe increased energy demands with quantization due to lower th…
Model CompressionQuantizationAda-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting
Continual Learning (CL) is a process in which there is still huge gap between human and deep learning model efficiency. Recently, many CL algorithms were designed. Most of them have many problems with learning in dynamic…
Continual LearningNon-Uniform Quantisation for 3DGS Compression
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, yet its high bitrate requirements pose significant challenges for storage and transmission. To enable practical applications and …
Novel View SynthesisEnergy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation
Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity.Since for those systems it is often required to operate both in…
Autonomous Vehicles