Learning Multimodal Fixed-Point Weights using Gradient Descent
arXiv:1907.07220
Abstract
Due to their high computational complexity, deep neural networks are still limited to powerful processing units. To promote a reduced model complexity by dint of low-bit fixed-point quantization, we propose a gradient-based optimization strategy to generate a symmetric mixture of Gaussian modes (SGM) where each mode belongs to a particular quantization stage. We achieve 2-bit state-of-the-art performance and illustrate the model's ability for self-dependent weight adaptation during training.
presented at ESANN 2019 (European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning)