[HTML][HTML] Deep physical neural networks trained with backpropagation
Deep-learning models have become pervasive tools in science and engineering. However,
their energy requirements now increasingly limit their scalability. Deep-learning …
their energy requirements now increasingly limit their scalability. Deep-learning …
Backpropagation-free training of deep physical neural networks
Recent successes in deep learning for vision and natural language processing are
attributed to larger models but come with energy consumption and scalability issues. Current …
attributed to larger models but come with energy consumption and scalability issues. Current …
Understanding deep learning is also a job for physicists
L Zdeborová - Nature Physics, 2020 - nature.com
Understanding deep learning is also a job for physicists | Nature Physics Skip to main content
Thank you for visiting nature.com. You are using a browser version with limited support for …
Thank you for visiting nature.com. You are using a browser version with limited support for …
End-to-end differentiable physics for learning and control
F de Avila Belbute-Peres, K Smith… - Advances in neural …, 2018 - proceedings.neurips.cc
We present a differentiable physics engine that can be integrated as a module in deep
neural networks for end-to-end learning. As a result, structured physics knowledge can be …
neural networks for end-to-end learning. As a result, structured physics knowledge can be …
Experimentally realized in situ backpropagation for deep learning in photonic neural networks
Integrated photonic neural networks provide a promising platform for energy-efficient, high-
throughput machine learning with extensive scientific and commercial applications. Photonic …
throughput machine learning with extensive scientific and commercial applications. Photonic …
Wave physics as an analog recurrent neural network
Analog machine learning hardware platforms promise to be faster and more energy efficient
than their digital counterparts. Wave physics, as found in acoustics and optics, is a natural …
than their digital counterparts. Wave physics, as found in acoustics and optics, is a natural …
All-optical spiking neurosynaptic networks with self-learning capabilities
Software implementations of brain-inspired computing underlie many important
computational tasks, from image processing to speech recognition, artificial intelligence and …
computational tasks, from image processing to speech recognition, artificial intelligence and …
An on-chip photonic deep neural network for image classification
F Ashtiani, AJ Geers, F Aflatouni - Nature, 2022 - nature.com
Deep neural networks with applications from computer vision to medical diagnosis,,,–are
commonly implemented using clock-based processors,,,,,,,–, in which computation speed is …
commonly implemented using clock-based processors,,,,,,,–, in which computation speed is …
[HTML][HTML] Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware
Ever-growing demand for artificial intelligence has motivated research on unconventional
computation based on physical devices. While such computation devices mimic brain …
computation based on physical devices. While such computation devices mimic brain …
Training of photonic neural networks through in situ backpropagation and gradient measurement
Recently, integrated optics has gained interest as a hardware platform for implementing
machine learning algorithms. Of particular interest are artificial neural networks, since matrix …
machine learning algorithms. Of particular interest are artificial neural networks, since matrix …