The CCC framework: Training and inference of a simple MLP for the XOR problem

In this work we consider a simple multilayer perceptron (MLP) for the 3-input XOR problem. We design and implement both training and inference stages from scratch, with hardware implementation in mind. We give our algorithm details, verify its correct functionality in GNU Ada and proceed with high-level synthesis, via our Custom Coprocessor Compilations (CCC) framework tool. Results validate our motivation for accelerated performance and device portability.