Wave Physics as an Analog Recurrent Neural Network
This work introduces a new class of analog processors for temporal data, potentially benefiting fields like signal processing and AI hardware, though it is incremental as it builds on existing analog and neural network concepts.
The authors tackled the problem of creating faster and energy-efficient analog machine learning hardware by mapping wave physics dynamics to recurrent neural network computations, demonstrating that an inverse-designed medium can perform vowel classification on raw audio with performance comparable to digital RNNs.
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.