“I keep running into sonoluminescence lately (https://en.wikipedia.org/wiki/Sonoluminescence), this kind of reminds me of that? Sonoluminescence reminds me of gravitational collapse, but I think that's probably because I need to read up more... Very interesting stuff going on with applied physics though--the most immediate application is probably material…”
Towards Trainable Media: Using Waves for Neural Network-Style Training
In this paper we study the concept of using the interaction between waves and a trainable medium in order to construct a matrix-vector multiplier. In particular we study such a device in the context of the backpropagation algorithm, which is commonly used for training neural networks. Here, the weights of the connections between neurons are trained by multiplying a `forward' signal with a backwards propagating `error' signal. We show that this concept can be extended to trainable media, where the gradient for the local wave number is given by multiplying signal waves and error waves. We provide a numerical example of such a system with waves traveling freely in a trainable medium, and we discuss a potential way to build such a device in an integrated photonics chip.
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- Using Light for Neural Networks Backpropagation ↗groar · 2015-10-15 · 3 分
- Using Waves for Neural Network-Style Training ↗bra-ket · 2015-10-27 · 3 分