Asymptotically fault-tolerant programmable photonics
R Hamerly, S Bandyopadhyay, D Englund - Nature Communications, 2022 - nature.com
Component errors limit the scaling of programmable coherent photonic circuits. These errors
arise because the standard tunable photonic coupler—the Mach-Zehnder interferometer …
arise because the standard tunable photonic coupler—the Mach-Zehnder interferometer …
Quantum-limited stochastic optical neural networks operating at a few quanta per activation
Energy efficiency in computation is ultimately limited by noise, with quantum limits setting the
fundamental noise floor. Analog physical neural networks hold promise for improved energy …
fundamental noise floor. Analog physical neural networks hold promise for improved energy …
Quantum-noise-limited optical neural networks operating at a few quanta per activation
A practical limit to energy efficiency in computation is ultimately from noise, with quantum
noise [1] as the fundamental floor. Analog physical neural networks [2], which hold promise …
noise [1] as the fundamental floor. Analog physical neural networks [2], which hold promise …
An optoacoustic field-programmable perceptron for recurrent neural networks
Recurrent neural networks (RNNs) can process contextual information such as time series
signals and language. But their tracking of internal states is a limiting factor, motivating …
signals and language. But their tracking of internal states is a limiting factor, motivating …
Quantum-secure multiparty deep learning
Secure multiparty computation enables the joint evaluation of multivariate functions across
distributed users while ensuring the privacy of their local inputs. This field has become …
distributed users while ensuring the privacy of their local inputs. This field has become …
All-optical nonlinear activation function based on stimulated Brillouin scattering
Optical neural networks have demonstrated their potential to overcome the computational
bottleneck of modern digital electronics. However, their development towards high …
bottleneck of modern digital electronics. However, their development towards high …
[HTML][HTML] Deep learning enabled photonic Nyquist folding receiver for wideband RF spectral analysis
The need for real-time wideband radio frequency (RF) spectral analysis is driven by
continued advances in modern wireless communications and RADAR systems used both for …
continued advances in modern wireless communications and RADAR systems used both for …
An integrated microwave neural network for broadband computation and communication
BAL GOVIND, M Anderson, F Wu, P McMahon, A Apsel - 2025 - researchsquare.com
High-bandwidth applications, from multi-gigabit communication and high-performance
computing to radar signal processing, demand ever-increasing processing speeds …
computing to radar signal processing, demand ever-increasing processing speeds …
Hyper-multiplexed, Ultralow-Energy Optical Neural Networks on Thin-Film Lithium Niobate
We demonstrate a large-scale wavelength-time-space-multiplexed optical neural network
using high-bandwidth (> 40 GHz) electro-optic modulators at CMOS-compatible voltages (V …
using high-bandwidth (> 40 GHz) electro-optic modulators at CMOS-compatible voltages (V …
Multiplexing methods for scaling up photonic logic
Existing photonic matrix processers are too small to tackle relevant problems. Here, I review
our group's recent work on scaling up analog photonic platforms. This work includes iterative …
our group's recent work on scaling up analog photonic platforms. This work includes iterative …