AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks
Not on the map. Why?
Abstract (arXiv)
AnalogVNN, a simulation framework built on PyTorch which can simulate the effects of optoelectronic noise, limited precision, and signal normalization present in photonic neural network accelerators. We use this framework to train and optimize linear and convolutional neural networks with up to 9 layers and ~1.7 million parameters, while gaining insights into how normalization, activation function, reduced precision, and noise influence accuracy in analog photonic neural networks. By following the same layer structure design present in PyTorch, the AnalogVNN framework allows users to convert most digital neural network models to their analog counterparts with just a few lines of code, taking full advantage of the open-source optimization, deep learning, and GPU acceleration libraries available through PyTorch. Code is available at https://analogvnn.github.io
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 72 references that are in the map. First posted on arXiv 14 Oct 2022.
Builds on
23 of 72 references.
References · 23
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2016Gaussian Error Linear Units (GELUs)cited by 3,431
- 2018Learning Dexterous In-Hand Manipulationcited by 643
- 2015Deep Learning with Limited Numerical Precisioncited by 368
- 2018How Does Batch Normalization Help Optimization?cited by 355
- 2017Don't Decay the Learning Rate, Increase the Batch Sizecited by 313
- 2017Train longer, generalize better: closing the generalization gap in large batch training of neural networkscited by 278
- 2020The Computational Limits of Deep Learningcited by 188
- 2018All-Optical Machine Learning Using Diffractive Deep Neural Networkscited by 175
- 2020Hyperparameter Selection for Offline Reinforcement Learningcited by 113
- 2020Photonics for artificial intelligence and neuromorphic computingcited by 111
11 more
- 2020Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unitcited by 64
- 2021Compute and Energy Consumption Trends in Deep Learning Inferencecited by 61
- 2017Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimizationcited by 56
- 2021A flexible and fast PyTorch toolkit for simulating training and inference on analog crossbar arrayscited by 38
- 2021An optical neural network using less than 1 photon per multiplicationcited by 30
- 2018Adversarial Noise Layer: Regularize Neural Network By Adding Noisecited by 25
- 2018RxNN: A Framework for Evaluating Deep Neural Networks on Resistive Crossbarscited by 17
- 2015Random Projections through multiple optical scattering: Approximating kernels at the speed of lightcited by 16
- 2021An Electro-Photonic System for Accelerating Deep Neural Networkscited by 15
- 2022Hyperparameter Tuning for Deep Reinforcement Learning Applicationscited by 7
- 2015The Effects of Hyperparameters on SGD Training of Neural Networkscited by 3
Built on by
Citing papers per year: 2024: 2.
2 papers.