# Quantisation and Pruning for Neural Network Compression and Regularisation

arXiv: https://arxiv.org/abs/2001.04850 · HTML: https://mlsanity.com/paper/2001.04850/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2020.

## Built on by (most cited first, 9 of 9)

- [Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression](https://mlsanity.com/paper/2109.03228/) (2021)
- [Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions](https://mlsanity.com/paper/2303.08595/) (2023)
- [Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations](https://mlsanity.com/paper/2110.08271/) (2021)
- [Benchmarking Quantized Neural Networks on FPGAs with FINN](https://mlsanity.com/paper/2102.01341/) (2021)
- [DASS: Differentiable Architecture Search for Sparse neural networks](https://mlsanity.com/paper/2207.06968/) (2022)
- [Verifiable and Energy Efficient Medical Image Analysis with Quantised Self-attentive Deep Neural Networks](https://mlsanity.com/paper/2209.15287/) (2022)
- [Tiny, On-Device Decision Makers with the MiniConv Library](https://mlsanity.com/paper/2512.19726/) (2025)
- [FCN-Pose: A Pruned and Quantized CNN for Robot Pose Estimation for Constrained Devices](https://mlsanity.com/paper/2205.13272/) (2022)
- [Structured Network Pruning by Measuring Filter-wise Interactions](https://mlsanity.com/paper/2307.00758/) (2023)

## Abstract (arXiv)

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.