Journal
SCIENCE ADVANCES
Volume 5, Issue 12, Pages -Publisher
AMER ASSOC ADVANCEMENT SCIENCE
DOI: 10.1126/sciadv.aay6946
Keywords
-
Categories
Funding
- Vannevar Bush Faculty Fellowship from the U.S. Department of Defense [N00014-17-1-3030]
- Gordon and Betty Moore Foundation [GBMF4744]
- MURI grant from the U.S. Air Force Office of Scientific Research [FA9550-171-0002]
- Swiss National Science Foundation [P300P2_177721]
- Swiss National Science Foundation (SNF) [P300P2_177721] Funding Source: Swiss National Science Foundation (SNF)
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available