RT Journal Article
SR Electronic
T1 Wave physics as an analog recurrent neural network
JF Science Advances
JO Sci Adv
FD American Association for the Advancement of Science
SP eaay6946
DO 10.1126/sciadv.aay6946
VO 5
IS 12
A1 Hughes, Tyler W.
A1 Williamson, Ian A. D.
A1 Minkov, Momchil
A1 Fan, Shanhui
YR 2019
UL http://advances.sciencemag.org/content/5/12/eaay6946.abstract
AB Analog machine learning hardware platforms promise to be faster and more energy efficient than their digital counterparts. Wave physics, as found in acoustics and optics, is a natural candidate for building analog processors for time-varying signals. Here, we identify a mapping between the dynamics of wave physics and the computation in recurrent neural networks. This mapping indicates that physical wave systems can be trained to learn complex features in temporal data, using standard training techniques for neural networks. As a demonstration, we show that an inverse-designed inhomogeneous medium can perform vowel classification on raw audio signals as their waveforms scatter and propagate through it, achieving performance comparable to a standard digital implementation of a recurrent neural network. These findings pave the way for a new class of analog machine learning platforms, capable of fast and efficient processing of information in its native domain.