A foundational component of vision processing is edge and feature detection. In the human eye, this is carried out powerfully via retinal ganglion cells which fight to suppress neuronal firing of neighbouring cells - a process termed 'lateral inhibition'.
Such spatially-distributed activity competition leads to strong nonlinear enhancement of key image features such as edges, enabling more complex vision functionality including object recognition & motion detection.
Software convolutional neural networks draw inspiration from this process and also begin with edge-detection, but in software this functionality is slow & the process intrinsically linear (matrix multiplications between the input image & convolutional kernels), with nonlinearity forced in via subsequent computationally-expensive activation functions such as ReLu.
Here, we present a physical system which reproduces the strongly nonlinear lateral inhibition used in the retina. Using spatially-distributed mode-competition in nanoscale random network lasers, we demonstrate cutting-edge feature detection on complex images, and leverage this for a retinomorphic photonic convolutional neural network with strong performance.
We show that a lithographically designable network of waveguides etched into a wafer-bonded layer of InP can act as a physical neuromorphic computing system. The network is a lasing medium, with many spatially complex and overlapping modes competing for gain. The complex nonlinear interaction between these modes enables spectrally multiplexed feature detection in image data optically projected onto the network, with different spectral regions corresponding to different features.
We use the network’s complex photonic dynamics to perform image classification tasks by training a single regression layer on the network’s spectral output, and construct a photonic convolutional neural network by combining the feature detection and classification layers, with 98.4% and 89.9% accuracies for MNIST and Fashion MNIST respectively.
Finally, we explore how the graph properties of the network and tuning illumination parameters impact the machine learning performance of the system.
We experimentally study the spectral lasing response of on-chip InP network random lasers under illumination of different input image shapes. Deep-learning models have become increasingly omipresent throughout society. However, they are blighted by exponentially soaring energy demands. Physical implementations of neural networks are emerging as an attractive solution for performing machine learning more energy-efficiently than conventional GPU hardware by mimicking the complex structure of biological brains. However, not many platforms which can natively receive unprocessed raw image data as light have so far been demonstrated – a highly-appealing approach which deserves attention. Here, we demonstrate an optical system with spectral response to image input. Specifically, we report on designable solid-state InP network random lasers, based on random graph networks etched into wafer-bonded InP. The networks lase over a broad wavelength range and show a plethora of modes formed by multiple scattering paths. These modes are highly sensitive to illumination patterns due to their unique and highly overlapping spatial distribution.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.