Jump to content

Binary neural network

From Simple English Wikipedia, the free encyclopedia
Revision as of 08:03, 5 December 2020 by Macdonald-ross (talk | changes) (Macdonald-ross moved page Binary Neural Network to Binary neural network: copy edit)

Binary neural network is an artificial neural network, where commonly used floating-point weights are replaced with binary ones.[1] It's largely saving the storage and computation, serves as a technique for deploying deep models on resource-limited devices. Usage of binary values can bring up to 58 times speedup,[2] while 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

  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.