Ultimate Anatome, the ultimate PyTorch library to analyze internal representation of neural networks

Brando Miranda

Permalink

https://hdl.handle.net/2142/112796 Copy

Description

Title

Ultimate Anatome, the ultimate PyTorch library to analyze internal representation of neural networks

Author(s)

Brando Miranda

Issue Date

2021-11-30

Keyword(s)

• pytorch
• deep learning
• machine learning
• neural networks
• artificial neural networks
• interpretable ai
• cca
• svcca
• pwcca
• opd
• cka

Abstract

Ultimate Anatome is a PyTorch library to analyze internal representation of neural networks. It is an adaptation and improvement on original Anatome library Ryuichiro Hataya. In particular, we take careful attention to the selection of data points to make your neural network comparisons valid. In addition, we implement the original way to process the features of convolution neural networks. In addition we keep improving the library. Code in https://github.com/brando90/ultimate-anatome and https://pypi.org/project/ultimate-anatome/.

Publisher

https://github.com/brando90/ultimate-anatome

Type of Resource

• text
• other

Permalink

• https://github.com/brando90/ultimate-anatome
• https://pypi.org/project/ultimate-anatome/
• http://hdl.handle.net/2142/112796

Owning Collections