“The paper is linked at the bottom of the article: Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems -- https://arxiv.org/abs/2104.13386 > physics-aware training (PAT)... allows us to efficiently and accurately execute the backpropagation algorithm on any sequence of physical input-output transformations, …”
Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
Deep neural networks have become a pervasive tool in science and engineering. However, modern deep neural networks' growing energy requirements now increasingly limit their scaling and broader use. We propose a radical alternative for implementing deep neural network models: Physical Neural Networks. We introduce a hybrid physical-digital algorithm called Physics-Aware Training to efficiently train sequences of controllable physical systems to act as deep neural networks. This method automatically trains the functionality of any sequence of real physical systems, directly, using backpropagation, the same technique used for modern deep neural networks. To illustrate their generality, we demonstrate physical neural networks with three diverse physical systems-optical, mechanical, and electrical. Physical neural networks may facilitate unconventional machine learning hardware that is orders of magnitude faster and more energy efficient than conventional electronic processors.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“Specifically to the point of the comparatively low reliability / high variation of analog systems: an interesting property of neural nets is that they can be robust relative to noise when trained with the same type of noise witnessed under inference. Whether or not speed/etc. would be better in the digital vs. analog design-space, it's an interesting thi…”