Skip to main content

Hebbian/Anti-Hebbian Learning for Pytorch

Project description

alt text

Figure 1: HaH block for image classification DNNs.

Hebbian/Anti-Hebbian Learning for Pytorch

If you have questions you can contact metehancekic [at] ucsb [dot] edu

Pre-requisites

Install the dependencies

numpy==1.20.2 torch==1.10.2

How to install

We have a pypi module which can be installed simply with following command:

pip install hahtorch

Or one can clone the repository.

git clone git@github.com:metehancekic/HaH.git

Experiments

We used CIFAR-10 image classification to show the effectiveness of our module. We train a VGG16 in standard fashion and train another VGG16 that contains HaHblocks with layer-wise HaHCost as a supplement.

CIFAR10 Image Classification with VGG16 model as Backbone

alt text

Figure 2: HaH VGG16, our proposed architecture for HaH training.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hahtorch-0.0.4.tar.gz (6.7 kB view details)

Uploaded Source

Built Distribution

hahtorch-0.0.4-py2.py3-none-any.whl (8.5 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file hahtorch-0.0.4.tar.gz.

File metadata

  • Download URL: hahtorch-0.0.4.tar.gz
  • Upload date:
  • Size: 6.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.7.12

File hashes

Hashes for hahtorch-0.0.4.tar.gz
Algorithm Hash digest
SHA256 47b81f602b82e9e0bb52c0b2332a8f71d425defc9bec4eec4160b6ae193058e0
MD5 e368b4596cc06a727d1c0bf484cac0c9
BLAKE2b-256 a74882168f18d05914b4cfc0eb239a768870ed02b190b26420865a889f28f253

See more details on using hashes here.

File details

Details for the file hahtorch-0.0.4-py2.py3-none-any.whl.

File metadata

  • Download URL: hahtorch-0.0.4-py2.py3-none-any.whl
  • Upload date:
  • Size: 8.5 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.7.12

File hashes

Hashes for hahtorch-0.0.4-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 861b568ab48495d4af962eec529bffb8bd0a80696429b2d828c9406361a4f260
MD5 2d4325d75828f366e00df4d1b951b455
BLAKE2b-256 e62ad79c998e7f97b4d936d5482e209cf920ed3ea4a3e4afc18fcbf5530483b8

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page