1.7k citations · 4.5k across the 54 of their papers we have counts for
8 papers · 1 filter
Silicon Photonic Architecture for Training Deep Neural Networks with Direct Feedback Alignment
Matthew J. Filipovich, Zhimu Guo, Mohammed Al-Qadasi +6
There has been growing interest in using photonic processors for performing neural network inference operations; however, these networks are currently trained using standard digita…
Silicon photonic-electronic neural network for fibre nonlinearity compensation
Chaoran Huang, Shinsuke Fujisawa, Thomas Ferreira de Lima +12
In optical communication systems, fibre nonlinearity is the major obstacle in increasing the transmission capacity. Typically, digital signal processing techniques and hardware are…
Photonic spiking neural networks and CMOS-compatible graphene-on-silicon spiking neurons
Aashu Jha, Chaoran Huang, Hsuan-Tung Peng +2
Spiking neural networks are known to be superior over artificial neural networks for their computational power efficiency and noise robustness. The benefits of spiking coupled with…
Scaling Up Silicon Photonic-based Accelerators: Challenges and Opportunities
M. A. Al-Qadasi, L. Chrostowski, B. J. Shastri +1
Digital accelerators in the latest generation of CMOS processes support multiply and accumulate (MAC) operations at energy efficiencies spanning 10-to-100~fJ/Op. But the operating…
A Photonic-Circuits-Inspired Compact Network: Toward Real-Time Wireless Signal Classification at the Edge
Hsuan-Tung Peng, Joshua Lederman, Lei Xu +5
Machine learning (ML) methods are ubiquitous in wireless communication systems and have proven powerful for applications including radio-frequency (RF) fingerprinting, automatic mo…
Prospects and applications of photonic neural networks
Chaoran Huang, Volker J. Sorger, Mario Miscuglio +13
Neural networks have enabled applications in artificial intelligence through machine learning, and neuromorphic computing. Software implementations of neural networks on convention…
Silicon microring synapses enable photonic deep learning beyond 9-bit precision
Weipeng Zhang, Chaoran Huang, Hsuan-Tung Peng +6
Deep neural networks (DNN) consist of layers of neurons interconnected by synaptic weights. A high bit-precision in weights is generally required to guarantee high accuracy in many…
Dynamic Precision Analog Computing for Neural Networks
Sahaj Garg, Joe Lou, Anirudh Jain +1
Analog electronic and optical computing exhibit tremendous advantages over digital computing for accelerating deep learning when operations are executed at low precision. In this w…