English

Learning Multimodal Fixed-Point Weights using Gradient Descent

Machine Learning 2019-07-18 v1 Computer Vision and Pattern Recognition

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.

Keywords

Cite

@article{arxiv.1907.07220,
  title  = {Learning Multimodal Fixed-Point Weights using Gradient Descent},
  author = {Lukas Enderich and Fabian Timm and Lars Rosenbaum and Wolfram Burgard},
  journal= {arXiv preprint arXiv:1907.07220},
  year   = {2019}
}

Comments

presented at ESANN 2019 (European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning)

R2 v1 2026-06-23T10:22:36.072Z