# PRUNIX: Non-Ideality Aware Convolutional Neural Network Pruning for Memristive Accelerators

arXiv: https://arxiv.org/abs/2202.01758 · HTML: https://mlsanity.com/paper/2202.01758/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 3 Feb 2022.

## Builds on (most cited first, 5 of 5)

- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence](https://mlsanity.com/paper/1905.13277/) (2019)
- [An Ultra-Efficient Memristor-Based DNN Framework with Structured Weight Pruning and Quantization Using ADMM](https://mlsanity.com/paper/1908.11691/) (2019)
- [Crossbar-aware neural network pruning](https://mlsanity.com/paper/1807.10816/) (2018)
- [Learning the Structure for Structured Sparsity](https://mlsanity.com/paper/1503.03082/) (2015)

## Abstract (arXiv)

In this work, PRUNIX, a framework for training and pruning convolutional neural networks is proposed for deployment on memristor crossbar based accelerators. PRUNIX takes into account the numerous non-ideal effects of memristor crossbars including weight quantization, state-drift, aging and stuck-at-faults. PRUNIX utilises a novel Group Sawtooth Regularization intended to improve non-ideality tolerance as well as sparsity, and a novel Adaptive Pruning Algorithm (APA) intended to minimise accuracy loss by considering the sensitivity of different layers of a CNN to pruning. We compare our regularization and pruning methods with other standards on multiple CNN architectures, and observe an improvement of 13% test accuracy when quantization and other non-ideal effects are accounted for with an overall sparsity of 85%, which is similar to other methods