# Training Competitive Binary Neural Networks from Scratch

arXiv: https://arxiv.org/abs/1812.01965 · HTML: https://mlsanity.com/paper/1812.01965/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2018.

## Built on by (most cited first, 4 of 4)

- [Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale](https://mlsanity.com/paper/2407.12327/) (2024)
- [BCNN: Binary Complex Neural Network](https://mlsanity.com/paper/2104.10044/) (2021)
- [Benchmarking Quantized Neural Networks on FPGAs with FINN](https://mlsanity.com/paper/2102.01341/) (2021)
- [FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation](https://mlsanity.com/paper/2203.12091/) (2022)

## Abstract (arXiv)

Convolutional neural networks have achieved astonishing results in different application areas. Various methods that allow us to use these models on mobile and embedded devices have been proposed. Especially binary neural networks are a promising approach for devices with low computational power. However, training accurate binary models from scratch remains a challenge. Previous work often uses prior knowledge from full-precision models and complex training strategies. In our work, we focus on increasing the performance of binary neural networks without such prior knowledge and a much simpler training strategy. In our experiments we show that we are able to achieve state-of-the-art results on standard benchmark datasets. Further, to the best of our knowledge, we are the first to successfully adopt a network architecture with dense connections for binary networks, which lets us improve the state-of-the-art even further.