Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks

no code implementations • 9 Mar 2022 • Dominika Przewlocka-Rus, Syed Shakib Sarwar, H. Ekin Sumbul, Yuecheng Li, Barbara De Salvo

Eventually, the experiments showed that for low bit width precision, non-uniform quantization performs better than uniform, and at the same time, PoT quantization vastly reduces the computational complexity of the neural network.

Quantization