exp-time-series-tools / manifold_learning

Worked examples about manifold learning using sklearn and jupyter

Manifold_Learning Repository

Worked examples about manifold learning using sklearn and jupyter - It's all a bit Work-In-Progress so the "should be working" notebooks are

• Manifold_S_Dataset.ipynb
• Manifold_S_Dataset_Morphed.ipynb
• Manifold_Sphere_Dataset.ipynb
• Manifold_Handwritten_Digits_Dataset.ipynb
• Manifold_tSNE_UMAP_Advanced.ipynb
• Manifold_Handwritten_Digits_Classification_WIP.ipynb

Slides

https://de.slideshare.net/StefanKhn4

Alternatively, there are some pdf versions of related talks in the repo, the latest version being Mcubed_20181016.pdf

In the latest slides there are even more links to useful resources - most probably the full list.

Methods covered (well, mentioned and used)

Dimensionality Reduction

• PCA - Principal Component Analysis
• GRP - Gaussian Random Projections
• SRP - Sparse Random Projections

Standard Manifold Learning

• LLE - Locally Linear Embedding (multiple variants)
• Isomap - Isometric Feature Mapping
• MDS - Multi-Dimensional Scaling
• Spectral Embedding (Laplacian Eigenmaps)
• LTSA - Local Tangent Space Alignment

Advanced Manifold Learning

• tSNE - t-Distributed Stochastic Neighbor Embedding
• UMAP - Uniform Manifold Approximation and Projection

Resources

Scikit-learn documentation

http://scikit-learn.org/stable/modules/manifold.html

http://scikit-learn.org/stable/auto_examples/manifold/plot_compare_methods.html

http://scikit-learn.org/stable/auto_examples/manifold/plot_manifold_sphere.html

http://scikit-learn.org/stable/modules/random_projection.html

http://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html

Github repo with worked examples

https://github.com/cc-skuehn/Manifold_Learning

Jupyter Lab

https://jupyterlab.readthedocs.io/en/stable/index.html

Citation

Scikit-learn: Machine Learning in Python, Pedregosa et al., JMLR 12, pp. 2825-2830, 2011.

http://jmlr.csail.mit.edu/papers/v12/pedregosa11a.html

tSNE

Original tSNE paper http://www.jmlr.org/papers/volume9/vandermaaten08a/vandermaaten08a.pdf

Distill is a great resource, not only for understanding tSNE! https://distill.pub/2016/misread-tsne/

Linear tSNE for the Web https://graphics.tudelft.nl/Publications-new/2018/PMHLEV18/pezotti.pdf

UMAP

Original UMAP paper https://arxiv.org/pdf/1802.03426.pdf

Github repo for UMAP (Python) https://github.com/lmcinnes/umap

You need to install UMAP first, follow the instructions: https://github.com/lmcinnes/umap#installing

Documentation https://umap-learn.readthedocs.io/en/latest/basic_usage.html

Author / Contact / Questions

Visit me on XING

https://www.xing.com/profile/Stefan_Kuehn46

But I am on LinkedIn as well...

https://www.linkedin.com/in/stefan-k%C3%BChn-020a34119/