Physics-aware Differentiable Discrete Codesign for Diffractive Optical
Neural Networks
- URL: http://arxiv.org/abs/2209.14252v1
- Date: Wed, 28 Sep 2022 17:13:28 GMT
- Title: Physics-aware Differentiable Discrete Codesign for Diffractive Optical
Neural Networks
- Authors: Yingjie Li, Ruiyang Chen, Weilu Gao, Cunxi Yu
- Abstract summary: This work proposes a novel device-to-system hardware-software codesign framework, which enables efficient training of Diffractive optical neural networks (DONNs)
Gumbel-Softmax is employed to enable differentiable discrete mapping from real-world device parameters into the forward function of DONNs.
The results have demonstrated that our proposed framework offers significant advantages over conventional quantization-based methods.
- Score: 12.952987240366781
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Diffractive optical neural networks (DONNs) have attracted lots of attention
as they bring significant advantages in terms of power efficiency, parallelism,
and computational speed compared with conventional deep neural networks (DNNs),
which have intrinsic limitations when implemented on digital platforms.
However, inversely mapping algorithm-trained physical model parameters onto
real-world optical devices with discrete values is a non-trivial task as
existing optical devices have non-unified discrete levels and non-monotonic
properties. This work proposes a novel device-to-system hardware-software
codesign framework, which enables efficient physics-aware training of DONNs
w.r.t arbitrary experimental measured optical devices across layers.
Specifically, Gumbel-Softmax is employed to enable differentiable discrete
mapping from real-world device parameters into the forward function of DONNs,
where the physical parameters in DONNs can be trained by simply minimizing the
loss function of the ML task. The results have demonstrated that our proposed
framework offers significant advantages over conventional quantization-based
methods, especially with low-precision optical devices. Finally, the proposed
algorithm is fully verified with physical experimental optical systems in
low-precision settings.
Related papers
- 1-bit Quantized On-chip Hybrid Diffraction Neural Network Enabled by Authentic All-optical Fully-connected Architecture [4.594367761345624]
This study introduces the Hybrid Diffraction Neural Network (HDNN), a novel architecture that incorporates matrix multiplication into DNNs.
utilizing a singular phase modulation layer and an amplitude modulation layer, the trained neural network demonstrated remarkable accuracies of 96.39% and 89% in digit recognition tasks.
arXiv Detail & Related papers (2024-04-11T02:54:17Z) - Optical Quantum Sensing for Agnostic Environments via Deep Learning [59.088205627308]
We introduce an innovative Deep Learning-based Quantum Sensing scheme.
It enables optical quantum sensors to attain Heisenberg limit (HL) in agnostic environments.
Our findings offer a new lens through which to accelerate optical quantum sensing tasks.
arXiv Detail & Related papers (2023-11-13T09:46:05Z) - Free-Space Optical Spiking Neural Network [0.0]
We introduce the Free-space Optical deep Spiking Convolutional Neural Network (OSCNN)
This novel approach draws inspiration from computational models of the human eye.
Our results demonstrate promising performance with minimal latency and power consumption compared to their electronic ONN counterparts.
arXiv Detail & Related papers (2023-11-08T09:41:14Z) - Forward-Forward Training of an Optical Neural Network [6.311461340782698]
We present an experiment utilizing multimode nonlinear wave propagation in an optical fiber demonstrating the feasibility of the FFA approach using an optical system.
The results show that incorporating optical transforms in multilayer NN architectures trained with the FFA, can lead to performance improvements.
arXiv Detail & Related papers (2023-05-30T16:15:57Z) - Physics-aware Roughness Optimization for Diffractive Optical Neural
Networks [15.397285424104469]
diffractive optical neural networks (DONNs) have shown promising advantages over conventional deep neural networks.
We propose a physics-aware diffractive optical neural network training framework to reduce the performance difference between numerical modeling and practical deployment.
arXiv Detail & Related papers (2023-04-04T03:19:36Z) - Globally Optimal Training of Neural Networks with Threshold Activation
Functions [63.03759813952481]
We study weight decay regularized training problems of deep neural networks with threshold activations.
We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
arXiv Detail & Related papers (2023-03-06T18:59:13Z) - Signal Detection in MIMO Systems with Hardware Imperfections: Message
Passing on Neural Networks [101.59367762974371]
In this paper, we investigate signal detection in multiple-input-multiple-output (MIMO) communication systems with hardware impairments.
It is difficult to train a deep neural network (DNN) with limited pilot signals, hindering its practical applications.
We design an efficient message passing based Bayesian signal detector, leveraging the unitary approximate message passing (UAMP) algorithm.
arXiv Detail & Related papers (2022-10-08T04:32:58Z) - Momentum Diminishes the Effect of Spectral Bias in Physics-Informed
Neural Networks [72.09574528342732]
Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs)
They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias.
In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
arXiv Detail & Related papers (2022-06-29T19:03:10Z) - Neural Operator with Regularity Structure for Modeling Dynamics Driven
by SPDEs [70.51212431290611]
Partial differential equations (SPDEs) are significant tools for modeling dynamics in many areas including atmospheric sciences and physics.
We propose the Neural Operator with Regularity Structure (NORS) which incorporates the feature vectors for modeling dynamics driven by SPDEs.
We conduct experiments on various of SPDEs including the dynamic Phi41 model and the 2d Navier-Stokes equation.
arXiv Detail & Related papers (2022-04-13T08:53:41Z) - An Adaptive Device-Edge Co-Inference Framework Based on Soft
Actor-Critic [72.35307086274912]
High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices.
We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations.
Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
arXiv Detail & Related papers (2022-01-09T09:31:50Z) - Physics-informed Neural Network for Nonlinear Dynamics in Fiber Optics [10.335960060544904]
A physics-informed neural network (PINN) that combines deep learning with physics is studied to solve the nonlinear Schr"odinger equation for learning nonlinear dynamics in fiber optics.
PINN is not only an effective partial differential equation solver, but also a prospective technique to advance the scientific computing and automatic modeling in fiber optics.
arXiv Detail & Related papers (2021-09-01T12:19:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.