1. On the RTL Implementation of FINN Matrix Vector Unit
2. FINN-
R
3. Chisel/FIRRTL Hardware Compiler Framework,0
4. HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks;dong;Advances in neural information processing systems,2020
5. DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients;zhou,2016