Data repository of the paper "Quantum-noise-limited optical neural networks operating at a few quanta per activation"
Authors/Creators
- 1. Cornell University
- 2. Cornell University, USRA Research Institute for Advanced Computer Science
- 3. Cornell University, NTT Research Inc.
Description
This data repository includes the requisite data and code for deriving the primary results from the paper, "Quantum-noise-limited optical neural networks operating at a few quanta per activation". The repository is structured to provide everything needed to reproduce the figures included in the main manuscript, along with the source code for training the neural network models and the collected experimental data mentioned in the paper.
The code in this repository is primarily intended for reproducing the results discussed in the paper. Those interested in developing their own applications may refer to our Github repository: https://github.com/mcmahon-lab/Single-Photon-Detection-Neural-Networks.
Where to Start
The directory 'main_figures' includes Jupyter notebooks to generate each panel in Figure 3 and Figure 4 in the main text, using the data from the directory 'results', which can be generated by notebooks in the directory 'test'.
The simulations, experiments, and figure generation were all conducted in Python. As certain parts of the code require specific versions of Python packages, the necessary packages are listed in the 'requirements.txt' file.
For more information, please refer to 'README.txt'.