Binary DNN for Intel Movidius Neural Compute Stick
Binarized Neural Networks http:https://papers.nips.cc/paper/6573-binarized-neural-networks.pdf
Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization (https://arxiv.org/abs/1906.02107)
https://www.youtube.com/watch?v=Q17HwA5oY4w
32 less memory 23x faster and much lower power consumption
Tutorial for Using Custom Layers with OpenVINO (Intel Deep Learning Toolkit) https://github.com/david-drew/OpenVINO-Custom-Layers