Compact optical convolution processing unit based on multimode interference
X. Meng,Guo Zhen Zhang,Nuannuan Shi,Guangyi Li,José Azaña,José Capmany,Jianping Yao,Yichen Shen,Wei Liu,Ninghua Zhu,Ming Li +10 more
TL;DR: In this paper , a compact on-chip optical convolutional processing unit is fabricated on a low-loss silicon nitride platform to demonstrate its capability for large-scale integration, and three 2 × 2 correlated real-valued kernels are made of two multimode interference cells and four phase shifters to perform parallel convolution operations.
read more
Abstract: Convolutional neural networks are an important category of deep learning, currently facing the limitations of electrical frequency and memory access time in massive data processing. Optical computing has been demonstrated to enable significant improvements in terms of processing speeds and energy efficiency. However, most present optical computing schemes are hardly scalable since the number of optical elements typically increases quadratically with the computational matrix size. Here, a compact on-chip optical convolutional processing unit is fabricated on a low-loss silicon nitride platform to demonstrate its capability for large-scale integration. Three 2 × 2 correlated real-valued kernels are made of two multimode interference cells and four phase shifters to perform parallel convolution operations. Although the convolution kernels are interrelated, ten-class classification of handwritten digits from the MNIST database is experimentally demonstrated. The linear scalability of the proposed design with respect to computational size translates into a solid potential for large-scale integration.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Optical neural networks: progress and challenges
Tingzhao Fu,Jianfa Zhang,Run Sun,Yuyao Huang,Sigang Yang,Zhihong Zhu,Hongwei Chen +6 more
16
Hybrid photonic integrated circuits for neuromorphic computing
Rongyang Xu,Shabnam Taheriniya,Anna P. Ovvyan,Rasmus Bankwitz,Liam McRae,Erik Jung,Frank Brückerhoff-Plückelmann,Ivonne Bente,Francesco Lenzini,Harish Bhaskaran,Wolfram Pernice +10 more
TL;DR: Researchers explore hybrid photonic integrated circuits for neuromorphic computing, a high-speed, energy-efficient approach to alleviate challenges in artificial intelligence, leveraging photonic platforms, materials, and hybrid devices for improved performance and data processing.
16
Photonic integrated neuro-synaptic core for convolutional spiking neural network
Shuiying Xiang,Yuechun Shi,Yahui Zhang,Xueyi Guo,Ling Zheng,Yanan Han,Yuna Zhang,Ziwei Song,Dianzhuang Zheng,Tao� Zhang,Hailin Wang,Xiao Zhu,Xiangfei Chen,Min Qiu,Yichen Shen,Wanhua Zheng,Yue Hao +16 more
TL;DR: Photonic integrated neuro-synaptic core for convolutional spiking neural network enables simultaneous implementation of linear weighting and nonlinear spike activation.
14
Integrated WDM-compatible optical mode division multiplexing neural network accelerator
Ruoyu Yin,Huifu Xiao,Yongheng Jiang,Xu Han,Pu Zhang,Li Shian Chen,Xudong Zhou,Mingrui Yuan,Guanghui Ren,Arnan Mitchell,Yonghui Tian +10 more
TL;DR: Researchers propose a photonic neural network accelerator using mode division multiplexing, reducing the need for multi-wavelength lasers and enabling efficient computation of both positive and negative values, achieving 1.37TOPS/mm² computing density.
13
References
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
- 01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
53.5K
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner,Patrick Haffner +7 more
- 01 Jan 2001
TL;DR: This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.
32.7K
Learning internal representations by error propagation
David E. Rumelhart,Geoffrey E. Hinton,Ronald J. Williams +2 more
- 01 Jan 1988
TL;DR: This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion.
•Book
Learning internal representations by error propagation
David E. Rumelhart,Geoffrey E. Hinton,Ronald J. Williams +2 more
- 03 Jan 1986
TL;DR: In this paper, the problem of the generalized delta rule is discussed and the Generalized Delta Rule is applied to the simulation results of simulation results in terms of the generalized delta rule.
16K