Nonlinear Computation with Linear Optics via Source-Position Encoding
This work addresses the problem of enabling efficient optical neural networks for machine learning applications, representing a novel method for a known bottleneck.
The authors tackled the challenge of implementing energy-efficient nonlinearities in optical computing for neural networks by introducing a method that achieves nonlinear computation in fully linear media using source-position encoding. They demonstrated significant improvements over linear methods and competitive performance compared to standard artificial neural networks on classification tasks.
Optical computing systems provide an alternate hardware model which appears to be aligned with the demands of neural network workloads. However, the challenge of implementing energy efficient nonlinearities in optics -- a key requirement for realizing neural networks -- is a conspicuous missing link. In this work we introduce a novel method to achieve nonlinear computation in fully linear media. Our method can operate at low power and requires only the ability to drive the optical system at a data-dependent spatial position. Leveraging this positional encoding, we formulate a fully automated, topology-optimization-based hardware design framework for extremely specialized optical neural networks, drawing on modern advancements in optimization and machine learning. We evaluate our optical designs on machine learning classification tasks: demonstrating significant improvements over linear methods, and competitive performance when compared to standard artificial neural networks.