Dense Associative Memory in a Nonlinear Optical Hopfield Neural Network

Abstract

Modern Hopfield Neural Networks (HNNs), also known as Dense Associative Memories (DAMs), enhance the performance of simple recurrent neural networks by leveraging the nonlinearities in their energy functions. They have broad applications in combinatorial optimization, high-capacity memory storage, deep learning transformers, and correlated pattern recognition. Thus far, research on DAMs has been primarily theoretical, with implementations limited to CPUs and GPUs. In this work, for the first time to our knowledge, we propose and experimentally demonstrate a nonlinear optical Hopfield neural network (NOHNN) system for realizing DAMs using correlated patterns. Our NOHNN incorporates effective 2-body and 4-body interactions in its energy function. The inclusion of 4-body interaction scores a minimum ten-fold improvement in the number of uncorrelated patterns that can be stored and retrieved, significantly surpassing the traditional capacity limit for traditional HNNs. For correlated patterns, depending on their average correlation, up to 50 times more patterns can be stored compared to traditional HNNs. To test the system's robustness, the benchmark testing is performed on MNIST handwritten digit patterns. The results show a 5.5 times improvement in the pattern storage along with the retrieval of cleaner and less noisy patterns. These results highlight the potential of nonlinear optical DAMs for practical applications in challenging big-data optimization, computer vision and graph network tasks.

32 pages

References in corpus (22)

• Deep Learning with Coherent Nanophotonic Circuits
• Photonics for artificial intelligence and neuromorphic computing
• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• The physics of optical computing
• Large-scale photonic Ising machine by spatial light modulation
• An optical neural network using less than 1 photon per multiplication
• Online learning of the transfer matrix of dynamic scattering media: wavefront shaping meets multidimensional time series
• On a model of associative memory with huge storage capacity
• Experimental Observation of Phase Transitions in Spatial Photonic Ising Machine
• Enhancing associative memory recall and storage capacity using confocal cavity QED
• Large-scale Ising Emulation with Four-Body Interaction and All-to-All Connection
• Low-rank combinatorial optimization and statistical learning by spatial photonic Ising machine
• The Exponential Capacity of Dense Associative Memories
• Quantum Codes from Neural Networks
• Neural networks with redundant representation: detecting the undetectable
• Wavelength-division multiplexing optical Ising simulator enabling fully programmable spin couplings and external magnetic fields
• Quantum-limited stochastic optical neural networks operating at a few quanta per activation
• Robust and Efficient Single-Pixel Image Classificationwith Nonlinear Optics
• Observation of Distinct Phase Transitions in a Nonlinear Optical Ising Machine
• Spatial-photonic Ising machine by space-division multiplexing with physically tunable coefficients of a multi-component model
• Quantum accelerated approach to the thermal state of classical spin systems with applications to pattern-retrieval in the Hopfield neural network
• Effect of spatial correlations on Hopfield Neural Network and Dense Associative Memories