mcmahon-lab/ONN-QAT-SQL
Scripts for training neural networks resistant to photon shot noise with quantization-aware training, together with the code for simulating neural network performance under shot noise.
This project helps researchers and engineers design and evaluate optical neural networks (ONNs) that can perform reliably even with very low light levels. It takes your ONN design and training parameters, applies quantization-aware training (QAT), and then simulates its performance under realistic photon shot noise. This is ideal for scientists and engineers working on optical computing hardware or applications requiring robust AI in noisy optical environments.
No commits in the last 6 months.
Use this if you are developing optical neural networks and need to ensure they can classify data accurately despite the inherent noise from individual photons.
Not ideal if you are working on software-only neural networks or do not need to simulate photon shot noise in optical systems.
Stars
19
Forks
2
Language
Jupyter Notebook
License
CC-BY-4.0
Category
Last pushed
Jan 31, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mcmahon-lab/ONN-QAT-SQL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-mmlab/mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
Xilinx/brevitas
Brevitas: neural network quantization in PyTorch
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...