https://github.com/mwrites/models-explained

A study of machine learning architectures
https://github.com/mwrites/models-explained

Last synced: 7 days ago
JSON representation

A study of machine learning architectures

• Host: GitHub
• URL: https://github.com/mwrites/models-explained
• Owner: mwrites
• License: mit
• Created: 2024-06-28T18:24:59.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-08-26T12:20:54.000Z (3 months ago)
• Last Synced: 2024-10-12T01:30:30.811Z (about 1 month ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 1.02 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# A study of machine learning architectures

# NLP

- [GPT - Self Attention Block (Decoder Only)](./gpt_self_attention.ipynb)

# Vision

- [VGG vs FCN](./vgg_vs_fcn.ipynb)

- [Why ResNets?](./why_resnet.ipynb)

# Optimization Algorithms

- [From Momentum To Adam](./from_momentum_to_adam.ipynb)

- [Weight Decay And Saddle Points](./saddle_points.ipynb)