Wave physics as an analog recurrent neural network
By Tyler W. Hughes, Ian A. D. Williamson, Momchil Minkov, Shanhui Fan. Science Advances, 2019
343 citations recorded by the source corpus.
Analog machine learning computations are performed passively by propagating light and sound waves through programmed materials. 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.
Subfields: Artificial Intelligence, Electrical and Electronic Engineering
View Paper: https://www.semanticscholar.org/paper/3029a4610f719c917db7eb1ac05cdb6120deadfb
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Peter Leonard McMahon
- Marin Soljačić
- Dirk Englund
- Shanhui Fan
- Gordon Wetzstein
- Demetri Psaltis
- Aydogan Ozcan
- Cornelia Denz
In Electrical and Electronic Engineering
- Peter Leonard McMahon
- Marin Soljačić
- Dirk Englund
- Shanhui Fan
- David A. B. Miller
- Logan G. Wright
- Demetri Psaltis
- Sylvain Gigan
Citations in the corpus
- Deep physical neural networks trained with backpropagation (2021, background): “14, 15).”
- Inference in artificial intelligence with deep optics and photonics (2020, methodology): “Interestingly, more complicated shapes of optimized inhomogeneous media can be used to implement recurrent neural networks, for example for vowel classification 50 .”