1tengji1

ceviche-challenges

A suite of photonic inverse design challenge problems for topology optimization benchmarking

PreFab

Artificial nanofabrication of integrated photonic circuits using deep learning

gdspy

Python module for creating GDSII stream files, usually CAD layouts.

PreFab

Prediction of fabrication variations in integrated photonic devices using deep learning

ICML-2023-DSGD-and-SAM

[ICML 2023] Decentralized SGD and Average-direction SAM are Asymptotically Equivalent

lumopt

Python based continuous adjoint optimization wrapper for Lumerical

sam

grcwa

Python implementation of rigorous coupled wave analysis, autograd supported for optimization purpose

NIDN

Neural Inverse Design of Nanostructures

photonics-opt-testbed

testbed problems for photonics optimization

IDToolkit

IDToolkit: A Toolkit for Benchmarking and Developing Inverse Design Algorithms in Nanophotonics, KDD'23

D2NN-with-Pytorch

Pytorch version of D2NN

gnp

gradient norm penalty

ASAM

Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.

loss-landscapes

Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch

spectral-density

Hessian spectral density estimation in TF and Jax

loss-landscape

Code for visualizing the loss landscape of neural nets

GAM

The official repo for CVPR2023 highlight paper "Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization".

aihwkit

IBM Analog Hardware Acceleration Kit

sam

SAM: Sharpness-Aware Minimization (PyTorch)

Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

PhyLL

lightning

[SIGCOMM 2023] Lightning: A Reconfigurable Photonic-Electronic SmartNIC for Fast and Energy-Efficient Inference

PINNs

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations

idrlnet

IDRLnet, a Python toolbox for modeling and solving problems through Physics-Informed Neural Network (PINN) systematically.

ubc

UBC Siepic Ebeam PDK from edx course

PDEBench

PDEBench: An Extensive Benchmark for Scientific Machine Learning

Lottery-Ticket-Hypothesis-in-Pytorch

This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" by Jonathan Frankle and Michael Carbin that can be easily adapted to any model/dataset.

ml_defense

ncps

PyTorch and TensorFlow implementation of NCP, LTC, and CfC wired neural models