# LB-CNN: An Open Source Framework for Fast Training of Light Binary Convolutional Neural Networks using Chainer and Cupy

arXiv: https://arxiv.org/abs/2106.15350 · HTML: https://mlsanity.com/paper/2106.15350/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 25 Jun 2021.

## Builds on (most cited first, 9 of 9)

- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)
- [Machine Learning at the Network Edge: A Survey](https://mlsanity.com/paper/1908.00080/) (2019)
- [Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence](https://mlsanity.com/paper/2002.04803/) (2020)
- [Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence](https://mlsanity.com/paper/1909.00560/) (2019)
- [Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?](https://mlsanity.com/paper/1806.07550/) (2018)
- [Local Binary Convolutional Neural Networks](https://mlsanity.com/paper/1608.06049/) (2016)
- [EffNet: An Efficient Structure for Convolutional Neural Networks](https://mlsanity.com/paper/1801.06434/) (2018)
- [NL-CNN: A Resources-Constrained Deep Learning Model based on Nonlinear Convolution](https://mlsanity.com/paper/2102.00227/) (2021)

## Abstract (arXiv)

Light binary convolutional neural networks (LB-CNN) are particularly useful when implemented in low-energy computing platforms as required in many industrial applications. Herein, a framework for optimizing compact LB-CNN is introduced and its effectiveness is evaluated. The framework is freely available and may run on free-access cloud platforms, thus requiring no major investments. The optimized model is saved in the standardized .h5 format and can be used as input to specialized tools for further deployment into specific technologies, thus enabling the rapid development of various intelligent image sensors. The main ingredient in accelerating the optimization of our model, particularly the selection of binary convolution kernels, is the Chainer/Cupy machine learning library offering significant speed-ups for training the output layer as an extreme-learning machine. Additional training of the output layer using Keras/Tensorflow is included, as it allows an increase in accuracy. Results for widely used datasets including MNIST, GTSRB, ORL, VGG show very good compromise between accuracy and complexity. Particularly, for face recognition problems a carefully optimized LB-CNN model provides up to 100% accuracies. Such TinyML solutions are well suited for industrial applications requiring image recognition with low energy consumption.