An Overview of Binarized Neural Networks

Binarized neural networks (BNNs) are an extreme version of quantized neural networks where all weights and activations are quantized to +/- 1. A key motivation for such a network is to enable one to run powerful neural networks on small battery-powered devices. This talk introduced BNNs, explained how one can train such a network and reviewed some recent work in the area.

Supplemental Resources

1. Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1, by Courbariaux et al.
2. A review of Binarized Neural Networks, by Simons et al.
3. An Empirical Study of Binarized Neural Networks’ Optimization, by Alizadeh et al.