# BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet

arXiv: https://arxiv.org/abs/1705.09864 · HTML: https://mlsanity.com/paper/1705.09864/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2017.

## Built on by (most cited first, 11 of 11)

- [A comprehensive review of Binary Neural Network](https://mlsanity.com/paper/2110.06804/) (2021)
- [Cross-Language Binary-Source Code Matching with Intermediate Representations](https://mlsanity.com/paper/2201.07420/) (2022)
- [Ultra-compact Binary Neural Networks for Human Activity Recognition on RISC-V Processors](https://mlsanity.com/paper/2205.12781/) (2022)
- [An Encoding Framework for Binarized Images using HyperDimensional Computing](https://mlsanity.com/paper/2312.00454/) (2023)
- [Elastic-Link for Binarized Neural Network](https://mlsanity.com/paper/2112.10149/) (2021)
- [Binary Neural Networks as a general-propose compute paradigm for on-device computer vision](https://mlsanity.com/paper/2202.03716/) (2022)
- [RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs](https://mlsanity.com/paper/2301.06193/) (2023)
- [ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters](https://mlsanity.com/paper/2407.04964/) (2024)
- [ENOS: Energy-Aware Network Operator Search for Hybrid Digital and Compute-in-Memory DNN Accelerators](https://mlsanity.com/paper/2104.05217/) (2021)
- [LAB: Learnable Activation Binarizer for Binary Neural Networks](https://mlsanity.com/paper/2210.13858/) (2022)
- [Cost-Driven Hardware-Software Co-Optimization of Machine Learning Pipelines](https://mlsanity.com/paper/2310.07940/) (2023)

## Abstract (arXiv)

Binary Neural Networks (BNNs) can drastically reduce memory size and accesses by applying bit-wise operations instead of standard arithmetic operations. Therefore it could significantly improve the efficiency and lower the energy consumption at runtime, which enables the application of state-of-the-art deep learning models on low power devices. BMXNet is an open-source BNN library based on MXNet, which supports both XNOR-Networks and Quantized Neural Networks. The developed BNN layers can be seamlessly applied with other standard library components and work in both GPU and CPU mode. BMXNet is maintained and developed by the multimedia research group at Hasso Plattner Institute and released under Apache license. Extensive experiments validate the efficiency and effectiveness of our implementation. The BMXNet library, several sample projects, and a collection of pre-trained binary deep models are available for download at https://github.com/hpi-xnor