1
|
Wang H, Hu J, Morandi A, Nardi A, Xia F, Li X, Savo R, Liu Q, Grange R, Gigan S. Large-scale photonic computing with nonlinear disordered media. NATURE COMPUTATIONAL SCIENCE 2024; 4:429-439. [PMID: 38877122 DOI: 10.1038/s43588-024-00644-1] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/06/2023] [Accepted: 05/14/2024] [Indexed: 06/16/2024]
Abstract
Neural networks find widespread use in scientific and technological applications, yet their implementations in conventional computers have encountered bottlenecks due to ever-expanding computational needs. Photonic computing is a promising neuromorphic platform with potential advantages of massive parallelism, ultralow latency and reduced energy consumption but mostly for computing linear operations. Here we demonstrate a large-scale, high-performance nonlinear photonic neural system based on a disordered polycrystalline slab composed of lithium niobate nanocrystals. Mediated by random quasi-phase-matching and multiple scattering, linear and nonlinear optical speckle features are generated as the interplay between the simultaneous linear random scattering and the second-harmonic generation, defining a complex neural network in which the second-order nonlinearity acts as internal nonlinear activation functions. Benchmarked against linear random projection, such nonlinear mapping embedded with rich physical computational operations shows improved performance across a large collection of machine learning tasks in image classification, regression and graph classification. Demonstrating up to 27,648 input and 3,500 nonlinear output nodes, the combination of optical nonlinearity and random scattering serves as a scalable computing engine for diverse applications.
Collapse
Affiliation(s)
- Hao Wang
- Laboratoire Kastler Brossel, École Normale Supérieure-Paris Sciences et Lettres Research University, Sorbonne Université, Centre National de la Recherche Scientifique, UMR 8552, Collège de France, Paris, France
- State Key Laboratory of Precision Space-Time Information Sensing Technology, Department of Precision Instrument, Tsinghua University, Beijing, China
| | - Jianqi Hu
- Laboratoire Kastler Brossel, École Normale Supérieure-Paris Sciences et Lettres Research University, Sorbonne Université, Centre National de la Recherche Scientifique, UMR 8552, Collège de France, Paris, France.
| | - Andrea Morandi
- ETH Zurich, Institute for Quantum Electronics, Department of Physics, Optical Nanomaterial Group, Zurich, Switzerland
| | - Alfonso Nardi
- ETH Zurich, Institute for Quantum Electronics, Department of Physics, Optical Nanomaterial Group, Zurich, Switzerland
| | - Fei Xia
- Laboratoire Kastler Brossel, École Normale Supérieure-Paris Sciences et Lettres Research University, Sorbonne Université, Centre National de la Recherche Scientifique, UMR 8552, Collège de France, Paris, France
| | - Xuanchen Li
- ETH Zurich, Institute for Quantum Electronics, Department of Physics, Optical Nanomaterial Group, Zurich, Switzerland
| | - Romolo Savo
- ETH Zurich, Institute for Quantum Electronics, Department of Physics, Optical Nanomaterial Group, Zurich, Switzerland
- Centro Ricerche Enrico Fermi, Rome, Italy
| | - Qiang Liu
- State Key Laboratory of Precision Space-Time Information Sensing Technology, Department of Precision Instrument, Tsinghua University, Beijing, China
| | - Rachel Grange
- ETH Zurich, Institute for Quantum Electronics, Department of Physics, Optical Nanomaterial Group, Zurich, Switzerland
| | - Sylvain Gigan
- Laboratoire Kastler Brossel, École Normale Supérieure-Paris Sciences et Lettres Research University, Sorbonne Université, Centre National de la Recherche Scientifique, UMR 8552, Collège de France, Paris, France.
| |
Collapse
|
2
|
Wang Z, Chen J, Gong M, Shao Z. Higher-order neurodynamical equation for simplex prediction. Neural Netw 2024; 173:106185. [PMID: 38387202 DOI: 10.1016/j.neunet.2024.106185] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Revised: 02/01/2024] [Accepted: 02/15/2024] [Indexed: 02/24/2024]
Abstract
It is demonstrated that higher-order patterns beyond pairwise relations can significantly enhance the learning capability of existing graph-based models, and simplex is one of the primary form for graphically representing higher-order patterns. Predicting unknown (disappeared) simplices in real-world complex networks can provide us with deeper insights, thereby assisting us in making better decisions. Nevertheless, previous efforts to predict simplices suffer from two issues: (i) they mainly focus on 2- or 3-simplices, and there are few models available for predicting simplices of arbitrary orders, and (ii) they lack the ability to analyze and learn the features of simplices from the perspective of dynamics. In this paper, we present a Higher-order Neurodynamical Equation for Simplex Prediction of arbitrary order (HNESP), which is a framework that combines neural networks and neurodynamics. Specifically, HNESP simulates the dynamical coupling process of nodes in simplicial complexes through different relations (i.e., strong pairwise relation, weak pairwise relation, and simplex) to learn node-level representations, while explaining the learning mechanism of neural networks from neurodynamics. To enrich the higher-order information contained in simplices, we exploit the entropy and normalized multivariate mutual information of different sub-structures of simplices to acquire simplex-level representations. Furthermore, simplex-level representations and multi-layer perceptron are used to quantify the existence probability of simplices. The effectiveness of HNESP is demonstrated by extensive simulations on seven higher-order benchmarks. Experimental results show that HNESP improves the AUC values of the state-of-the-art baselines by an average of 8.32%. Our implementations will be publicly available at: https://github.com/jianruichen/HNESP.
Collapse
Affiliation(s)
- Zhihui Wang
- Key Laboratory of Modern Teaching Technology, Ministry of Education, Xi'an, China; School of Computer Science, Shaanxi Normal University, Xi'an, China.
| | - Jianrui Chen
- Key Laboratory of Modern Teaching Technology, Ministry of Education, Xi'an, China; School of Computer Science, Shaanxi Normal University, Xi'an, China.
| | - Maoguo Gong
- Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xi'an, China; School of Electronic Engineering, Xidian University, Xi'an, China.
| | - Zhongshi Shao
- Key Laboratory of Modern Teaching Technology, Ministry of Education, Xi'an, China; School of Computer Science, Shaanxi Normal University, Xi'an, China.
| |
Collapse
|
3
|
Nakajima M, Inoue K, Tanaka K, Kuniyoshi Y, Hashimoto T, Nakajima K. Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware. Nat Commun 2022; 13:7847. [PMID: 36572696 PMCID: PMC9792515 DOI: 10.1038/s41467-022-35216-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2021] [Accepted: 11/23/2022] [Indexed: 12/28/2022] Open
Abstract
Ever-growing demand for artificial intelligence has motivated research on unconventional computation based on physical devices. While such computation devices mimic brain-inspired analog information processing, the learning procedures still rely on methods optimized for digital processing such as backpropagation, which is not suitable for physical implementation. Here, we present physical deep learning by extending a biologically inspired training algorithm called direct feedback alignment. Unlike the original algorithm, the proposed method is based on random projection with alternative nonlinear activation. Thus, we can train a physical neural network without knowledge about the physical system and its gradient. In addition, we can emulate the computation for this training on scalable physical hardware. We demonstrate the proof-of-concept using an optoelectronic recurrent neural network called deep reservoir computer. We confirmed the potential for accelerated computation with competitive performance on benchmarks. Our results provide practical solutions for the training and acceleration of neuromorphic computation.
Collapse
Affiliation(s)
- Mitsumasa Nakajima
- NTT Device Technology Labs., 3-1 Morinosato-Wakamiya, Atsugi, Kanagwa 243-0198 Japan
| | - Katsuma Inoue
- grid.26999.3d0000 0001 2151 536XGraduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656 Japan
| | - Kenji Tanaka
- NTT Device Technology Labs., 3-1 Morinosato-Wakamiya, Atsugi, Kanagwa 243-0198 Japan
| | - Yasuo Kuniyoshi
- grid.26999.3d0000 0001 2151 536XGraduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656 Japan ,grid.26999.3d0000 0001 2151 536XNext Generation Artificial Intelligence Research Center, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656 Japan
| | - Toshikazu Hashimoto
- NTT Device Technology Labs., 3-1 Morinosato-Wakamiya, Atsugi, Kanagwa 243-0198 Japan
| | - Kohei Nakajima
- grid.26999.3d0000 0001 2151 536XGraduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656 Japan ,grid.26999.3d0000 0001 2151 536XNext Generation Artificial Intelligence Research Center, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656 Japan
| |
Collapse
|