# AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks

arXiv: https://arxiv.org/abs/2210.10048 · HTML: https://mlsanity.com/paper/2210.10048/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 72 references that are in the map.
- First posted on arXiv 14 Oct 2022.

## Builds on (most cited first, 23 of 23)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [How Does Batch Normalization Help Optimization?](https://mlsanity.com/paper/1805.11604/) (2018)
- [Don't Decay the Learning Rate, Increase the Batch Size](https://mlsanity.com/paper/1711.00489/) (2017)
- [Train longer, generalize better: closing the generalization gap in large batch training of neural networks](https://mlsanity.com/paper/1705.08741/) (2017)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [All-Optical Machine Learning Using Diffractive Deep Neural Networks](https://mlsanity.com/paper/1804.08711/) (2018)
- [Hyperparameter Selection for Offline Reinforcement Learning](https://mlsanity.com/paper/2007.09055/) (2020)
- [Photonics for artificial intelligence and neuromorphic computing](https://mlsanity.com/paper/2011.00111/) (2020)
- [Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit](https://mlsanity.com/paper/2008.11659/) (2020)
- [Compute and Energy Consumption Trends in Deep Learning Inference](https://mlsanity.com/paper/2109.05472/) (2021)
- [Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization](https://mlsanity.com/paper/1710.05179/) (2017)
- [A flexible and fast PyTorch toolkit for simulating training and inference on analog crossbar arrays](https://mlsanity.com/paper/2104.02184/) (2021)
- [An optical neural network using less than 1 photon per multiplication](https://mlsanity.com/paper/2104.13467/) (2021)
- [Adversarial Noise Layer: Regularize Neural Network By Adding Noise](https://mlsanity.com/paper/1805.08000/) (2018)
- [RxNN: A Framework for Evaluating Deep Neural Networks on Resistive Crossbars](https://mlsanity.com/paper/1809.00072/) (2018)
- [Random Projections through multiple optical scattering: Approximating kernels at the speed of light](https://mlsanity.com/paper/1510.06664/) (2015)
- [An Electro-Photonic System for Accelerating Deep Neural Networks](https://mlsanity.com/paper/2109.01126/) (2021)
- [Hyperparameter Tuning for Deep Reinforcement Learning Applications](https://mlsanity.com/paper/2201.11182/) (2022)
- [The Effects of Hyperparameters on SGD Training of Neural Networks](https://mlsanity.com/paper/1508.02788/) (2015)

## Built on by (most cited first, 2 of 2)

- [Leveraging Continuously Differentiable Activation Functions for Learning in Quantized Noisy Environments](https://mlsanity.com/paper/2402.02593/) (2024)
- [Thermal Crosstalk Modelling and Compensation Methods for Programmable Photonic Integrated Circuits](https://mlsanity.com/paper/2404.10589/) (2024)

## 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