Binary neural network

From Simple English Wikipedia, the free encyclopedia
Jump to navigation Jump to search

Binary neural network is an artificial neural network, where commonly used floating-point weights are replaced with binary ones.[1]

It saves storage and computation, and serves as a technique for deep models on resource-limited devices. Using binary values can bring up to 58 times speedup.[2] Accuracy and information capacity of binary neural network can be manually controlled.[3] Binary neural networks do not achieve the same accuracy as their full-precision counterparts, but improvements are being made to close this gap.

References[change | change source]

  1. Courbariaux, M.; Bengio, Y.; David, J.-P. (2015). "BinaryConnect: training deep neural networks with binary weights during propagation". NIPS. arXiv:1511.00363.
  2. Rastegari, M.; Ordonez, V.; Redmon, J.; Farhadi, A. (2016). "XNOR-Net: ImageNet classification using binary convolutional neural networks". ECCV. arXiv:1603.05279.
  3. Ignatov, D.; Ignatov, A. (2020). "Controlling information capacity of binary neural network". Pattern Recognition Letters. arXiv:2008.01438. doi:10.1016/j.patrec.2020.07.033.