https://github.com/xnought/vae-explainer

Interactive Variational Autoencoder (VAE)
https://github.com/xnought/vae-explainer

keras ml tfjs

Last synced: 4 months ago
JSON representation

Interactive Variational Autoencoder (VAE)

• Host: GitHub
• URL: https://github.com/xnought/vae-explainer
• Owner: xnought
• License: mit
• Created: 2024-08-31T14:04:16.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-09-16T01:03:04.000Z (5 months ago)
• Last Synced: 2024-09-30T10:02:21.557Z (4 months ago)
• Topics: keras, ml, tfjs
• Language: Jupyter Notebook
• Homepage: https://xnought.github.io/vae-explainer/
• Size: 15.7 MB
• Stars: 32
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


Learn how Variational Autoencoders (VAE) work by visualizing one running in your browser. 

- Live Site: https://xnought.github.io/vae-explainer/

- Paper: https://arxiv.org/abs/2409.09011

https://github.com/user-attachments/assets/ef788f0a-9c66-48fb-99d9-f4feb62ca9cd

## Development

```bash

pnpm install

pnpm dev

```

which runs the hot-reloading dev server at http://localhost:5173

## Cite

```bibtex

@misc{bertucci2024vaeexplainer,

      title={VAE Explainer: Supplement Learning Variational Autoencoders with Interactive Visualization}, 

      author={Donald Bertucci and Alex Endert},

      year={2024},

      eprint={2409.09011},

      archivePrefix={arXiv},

      primaryClass={cs.HC},

      url={https://arxiv.org/abs/2409.09011}, 

}

```

## Code References

- https://keras.io/examples/generative/vae/

- https://www.ibm.com/think/topics/variational-autoencoder#:~:text=Variational%20autoencoders%20(VAEs)%20are%20generative,other%20autoencoders%2C%20such%20as%20denoising.

- https://www.youtube.com/watch?v=9zKuYvjFFS8

- https://arxiv.org/abs/1312.6114 (original VAE paper)

- https://www.youtube.com/watch?v=afNuE5z2CQ8

- https://keras.io/examples/keras_recipes/trainer_pattern/