Feature Interpretability
The feature interpretability code is a python module that interprets and analyzes neural networks trained on hydrodynamic simulation output in the form of numpy arrays. The code takes trained neural networks and extracts internal model states in the form of images. Additionally, tools for covariance analysis of network weights and predictions are provided. This code is built on the TensorFlow and PyTorch python libraries, and includes trained networks and example input data for demonstration purposes.
- Site Accession Number:
- O4675
- Software Type:
- Scientific
- License(s):
- BSD 3-clause "New" or "Revised" License
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)Primary Award/Contract Number:AC52-06NA25396
- DOE Contract Number:
- AC52-06NA25396
- Code ID:
- 121161
- OSTI ID:
- code-121161
- Country of Origin:
- United States
Similar Records
Hyperparameter Studies for Vision Transformers Trained on High-Fidelity Simulations
PyTorch Implementation of Log-Additive Convolutional Neural Networks
LCA-PyTorch
Software
·
Tue May 28 20:00:00 EDT 2024
·
OSTI ID:code-134596
PyTorch Implementation of Log-Additive Convolutional Neural Networks
Software
·
Wed May 15 20:00:00 EDT 2024
·
OSTI ID:code-140120
LCA-PyTorch
Software
·
Thu Jun 22 20:00:00 EDT 2023
·
OSTI ID:code-110613