A PyTorch Library for Photonic AI Computing Model Training and Co-Design (NeurIPS'21)

Differentiable wave optics simulation library built on PyTorch

Supporting code for "End-to-end optical backpropagation for training neural networks".

SmartGlass (SG) is a python implementation of a diffractive optical neural network. Currently, it supports training an all-optical classifier (e.g. classify hand-written digits MNIST dataset). Besides, the framework can also be used to design optics based on a task like focusing and beam steering. However, custom object functions should be defin…

Machine Learning-Enabled Compact Photonic Tensor Core based on Programmable Multi-Operand Multimode Interference

This is a transaction-level, event-driven python-based simulator for evaluation of stochastic computing based optical neural network accelerators for various quantized Convolutional Neural Network models. This can generate metrics of an accelerator like latency, area, energy consumption and power

Official pytorch implementation of the paper: "Coherence Awareness in Diffractive Neural Networks"

This project uses an optics-informed backpropagation algorithm to train diffractive neural network architectures efficiently.

This repository accompanies “Free-Space Coherent Optical Dot-Product Multiplier with Lensless Fan-In” (Duque et al., 2026). It provides simulation code for a coherent free-space optical dot-product system using DMD/SLM-style modulation and camera-like readout.