{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/quantisation-and-pruning-for-neural-network","title":"Quantisation and Pruning for Neural Network Compression and Regularisation","arxiv_id":"2001.04850","date":"2020-01-14","proceeding":null,"authors":["Kimessha Paupamah","Steven James","Richard Klein"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2001.04850v1","url_pdf":"https://arxiv.org/pdf/2001.04850v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"quantisation-and-pruning-for-neural-network","repo_url":"https://github.com/kpaupamah/compression-and-regularisation","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"},{"task_slug":"neural-network-compression","task_name":"Neural Network Compression"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"channel-shuffle","method_name":"Channel Shuffle"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"groupwise-point-convolution","method_name":"Groupwise Point Convolution"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"mobilenetv1","method_name":"MobileNetV1"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"shufflenet","method_name":"ShuffleNet"},{"method_slug":"shufflenet-block","method_name":"ShuffleNet Block"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/network-pruning-on-cifar-10","task":"Network Pruning","dataset":"CIFAR-10","model":"MobileNet – Quantised","rank_in_archive_order":2,"of":4,"metrics":{"Inference Time (ms)":"4.74"},"uses_additional_data":false},{"leaderboard":"/sota/network-pruning-on-cifar-10","task":"Network Pruning","dataset":"CIFAR-10","model":"AlexNet – Quantised","rank_in_archive_order":3,"of":4,"metrics":{"Inference Time (ms)":"5.23"},"uses_additional_data":false},{"leaderboard":"/sota/network-pruning-on-cifar-10","task":"Network Pruning","dataset":"CIFAR-10","model":"ShuffleNet – Quantised","rank_in_archive_order":4,"of":4,"metrics":{"Inference Time (ms)":"23.15"},"uses_additional_data":false},{"leaderboard":"/sota/neural-network-compression-on-cifar-10","task":"Neural Network Compression","dataset":"CIFAR-10","model":"ShuffleNet – Quantised","rank_in_archive_order":1,"of":5,"metrics":{"Size (MB)":"1.9"},"uses_additional_data":false},{"leaderboard":"/sota/neural-network-compression-on-cifar-10","task":"Neural Network Compression","dataset":"CIFAR-10","model":"MobileNet – Quantised","rank_in_archive_order":2,"of":5,"metrics":{"Size (MB)":"2.9"},"uses_additional_data":false},{"leaderboard":"/sota/neural-network-compression-on-cifar-10","task":"Neural Network Compression","dataset":"CIFAR-10","model":"AlexNet – Quantised","rank_in_archive_order":3,"of":5,"metrics":{"Size (MB)":"54.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2001.04850","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}