https://github.com/tschechlovdev/autoencoder_kmeans
Implementation of AutoEncoder in PyTorch for k-Means Clustering
https://github.com/tschechlovdev/autoencoder_kmeans
auto-encoder clustering deep-learning pytorch
Last synced: 8 months ago
JSON representation
Implementation of AutoEncoder in PyTorch for k-Means Clustering
- Host: GitHub
- URL: https://github.com/tschechlovdev/autoencoder_kmeans
- Owner: tschechlovdev
- Created: 2024-05-07T07:12:28.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-06-10T07:53:25.000Z (almost 2 years ago)
- Last Synced: 2025-07-24T13:57:34.230Z (10 months ago)
- Topics: auto-encoder, clustering, deep-learning, pytorch
- Language: Jupyter Notebook
- Homepage:
- Size: 23 MB
- Stars: 4
- Watchers: 1
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Implementation of Auto-Encoders for k-Means Clustering
This is the implementation of my medium article ["Deep Auto-Encoders for Clustering: Understanding and Implementing in PyTorch"](https://medium.com/@tschechd/deep-auto-encoders-for-clustering-understanding-and-implementing-in-pytorch-8cc748a5fa48).
This repository showcases how to apply Auto-Encoders to learn a lower-dimensional and easier separable presentation of the data.
This is especially useful for tasks like clustering.
To this end, the well-known MNIST dataset that comprises images of handwritten digits is used.
The Auto-Encoder is implemented using PyTorch and scikit-learn is used to apply clustering.
The notebook shows that the accuracy of k-Means clustering can be improved by more than 20%-points using Auto-Encoders!