Model quantization with direct feedback alignment

Randy Widialaksono · March 2, 2020

In this experiment we compare MNIST training performance on the LeNet-5 model with three different training algorithms with/without 4-bit quantization. The three training algorithms are backpropagation (BP), feedback alignment (FA), and directed feedback alignment (DFA). We chose the 4-bit quantization to establish a baseline reference for the proposed work on binarization, namely quantized DFA (QDFA). The network consists of 2 convolution networks followed by 3 fully-connected layers.

MNIST Accuracy

Model topology: CONV6_MaxPool_CONV16_MaxPool_FC120_FC84_FC10

The quantization library used was Xilinx Brevitas (, while the feedback alignment implementation used was based from this repository on Direct Random Target Projection (

Twitter, Facebook