Ping Huang

A parallel computer clusters for convolutional network

2016

Convolution neural network can gain optional solution by training dataset many times. But persons without experiments are very difficult to seek a good learning rate or a good convergence criterion. We propose a framework, which …

BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer

2021 · arXiv (Cornell University)

As the applications of deep learning models on edge devices increase at an accelerating pace, fast adaptation to various scenarios with varying resource constraints has become a crucial aspect of model deployment. As a result, …