Skip to main content

My implementation of a random selection of artificial neural net based models.

Project description

random neural nets

Implementations of a random selection of artificial neural net based models and methods.

Python version

Development is done using pyenv, pinning the python version to the one in the file .python-version.

Installation (on Linux)

Package + notebooks:

git clone https://github.com/eschmidt42/random-neural-net-models.git
cd random-neural-net-models
make install

Package only:

pip install random-neural-net-models

Usage

See jupyter notebooks in nbs/ for:

  • perceptron: perceptron.ipynb
  • backpropagation: backpropagation_rumelhart1986.ipynb
  • convolution: convolution_lecun1990.ipynb
  • cnn autoencoder:
    • mnist: cnn_autoencoder_fastai2022.ipynb
    • fashion mnist: cnn_autoencoder_fastai2022_fashion.ipynb
  • variational autoencoder:
    • dense: dense_variational_autoencoder_fastai2022.ipynb
    • cnn+dense: cnn_variational_autoencoder_fastai2022.ipynb
  • optimizers: stochastic_optimization_methods.ipynb
  • resnet: resnet_fastai2022.ipynb
  • unet: unet_fastai2022.ipynb

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

random-neural-net-models-0.1.4.tar.gz (17.3 kB view details)

Uploaded Source

Built Distribution

random_neural_net_models-0.1.4-py3-none-any.whl (20.7 kB view details)

Uploaded Python 3

File details

Details for the file random-neural-net-models-0.1.4.tar.gz.

File metadata

File hashes

Hashes for random-neural-net-models-0.1.4.tar.gz
Algorithm Hash digest
SHA256 4622cadb45defac5081a37ed661250b4939b80837f769d55da045891f5619b77
MD5 11abaec8eafa022956263c4ff78579d5
BLAKE2b-256 ac461373615b41bcdce3579b62b8c71fcd03b372b979e1b92750fcc9ce2bddc9

See more details on using hashes here.

File details

Details for the file random_neural_net_models-0.1.4-py3-none-any.whl.

File metadata

File hashes

Hashes for random_neural_net_models-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 a72f731658a749ed86fb76182528dbab61823f6795cae75f8568d37d635e9b35
MD5 6de66c7c037fd034ab5f4fcaffaeabc3
BLAKE2b-256 757e41ced3bc1d693e36f5004999a729f24f92720e5a61d996a6c5e8c46e7cd8

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