The Next Generation of Deep Learning Hardware: Analog Computing.
Proceedings of the IEEE(2019)
摘要
Initially developed for gaming and 3-D rendering, graphics processing units (GPUs) were recognized to be a good fit to accelerate deep learning training. Its simple mathematical structure can easily be parallelized and can therefore take advantage of GPUs in a natural way. Further progress in compute efficiency for deep learning training can be made by exploiting the more random and approximate na...
更多查看译文
关键词
Analog computing,Machine learning,Convolution,Hardware,Deep learning,Graphics processing units,Nonvolatile memory,Neural networks,Nonvolatile memory
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络