DeepAI AI Chat
Log In Sign Up

Wave-based extreme deep learning based on non-linear time-Floquet entanglement

by   Ali Momeni, et al.

Wave-based analog signal processing holds the promise of extremely fast, on-the-fly, power-efficient data processing, occurring as a wave propagates through an artificially engineered medium. Yet, due to the fundamentally weak non-linearities of traditional wave materials, such analog processors have been so far largely confined to simple linear projections such as image edge detection or matrix multiplications. Complex neuromorphic computing tasks, which inherently require strong non-linearities, have so far remained out-of-reach of wave-based solutions, with a few attempts that implemented non-linearities on the digital front, or used weak and inflexible non-linear sensors, restraining the learning performance. Here, we tackle this issue by demonstrating the relevance of Time-Floquet physics to induce a strong non-linear entanglement between signal inputs at different frequencies, enabling a power-efficient and versatile wave platform for analog extreme deep learning involving a single, uniformly modulated dielectric layer and a scattering medium. We prove the efficiency of the method for extreme learning machines and reservoir computing to solve a range of challenging learning tasks, from forecasting chaotic time series to the simultaneous classification of distinct datasets. Our results open the way for wave-based machine learning with high energy efficiency, speed, and scalability.


page 3

page 7

page 11


Wave Physics as an Analog Recurrent Neural Network

Analog machine learning hardware platforms promise to be faster and more...

A Deep Learning Technique to Control the Non-linear Dynamics of a Gravitational-wave Interferometer

In this work we developed a deep learning technique that successfully so...

Single-Carrier Modulation versus OFDM for Millimeter-Wave Wireless MIMO

This paper presents results on the achievable spectral efficiency and on...

Photonic reservoir computing enabled by stimulated Brillouin scattering

Artificial Intelligence (AI) drives the creation of future technologies ...

Destructive Read by Wave Interference for Arbitration

With the advent of big data and deep learning, computation power has bec...

A new mathematical model for dispersion of Rayleigh wave and a machine learning based inversion solver

In this work, by introducing the seismic impedance tensor we propose a n...