Unsupervised and Reinforcement Learning (URL)

2020 Spring Term

Lecture Notes

These lecture notes cover all the topics of the course for the unsupervised learning part. You must read the chapter corresponding to the lecture of the week to be able to follow the class and to work with the practical exercises solved during the class.

This is a link to the python notebooks from github used in class (there are non interactive versions, see info about how to run them in the software section)

This is a link to the notebooks uploaded to Microsoft Azure platform (if you have a MS account you can sign in and clone the notebooks)

Slides and other material

This is a book that collects all the slides of the course, you have the slides by topic and the complementary material below.

1. Data Mining, a global perspective
   • Slides Introduction to Data Mining
   • From Data Mining To knowledge Discovery in Databases, Usama Fayyad, Gregory Piatetsky-Shapiro, and Padhraic Smyth
2. Data preprocessing/transformation
   • Slides Data preprocessing/Transformation
     
   • Algorithms for Clustering Data, Chapter 2 , Jain & Dubes
   • Continuous attributes discretization
   • Dimensionality Reduction: PCA, ICA, Multidimensional Scalling, Random Projection, Locally linear embedding, ISOMAP
   • Dimensionality reduction: Checkout also the sections 5 to 9 of chapter 14 of the book "The Elements of Statistical Learning" Hastie, Tibshirani, Friedman
   • Datasets: authors, wheel
     
3. Unsupervised machine learning
   • Slides about unsupervised learning algorithms
     
   • Slides about clustering evaluation
   • Unsupervised learning
   • Data Clustering: A Review (1999) A K Jain, M N Murty, P J Flynn ACM Computing Surveys
   • Algorithms for Clustering Data, Capitulo 3 , Jain & Dubes
   • Survey of clustering data mining techniques Pavel Berkhin
   • Checkout also sections 1 to 8 of of the book "The Elements of Statistical Learning" Hastie, Tibshirani, Friedman
   • Models of incremental concept formation J. Gennari, P. Langley, D. Fisher
   • A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise (DBSCAN) Martin Ester, Hans-Peter Kriegel, Jörg Sander, Xiaowei Xu
   • STING: A statistical information GRID approach to spatial datamining Wang, Yang, Muntz
   • An efficient approach to clustering in large multimedia databases witn noise (DENCLUE) Hinnenburg, Keim
   • Automatic Subspace Clustering of High Dimensional Data for Data Mining Applications (CLIQUE) (1998) Rakesh Agrawal Johannes Gehrke Dimitrios Gunopulos Prabhakar Raghavan
   • Evaluaton of clustering
   • Unsupervised learning evaluation (part 1 y part 2)
   • Comparison of clusterings
4. Unsupervised methodologies in Knowledge Discovery and Data Mining
• Slides Clustering methodologies in Knowledge discovery
• Unsupervised methodologies in Data Mining
  
  • Scaling Clustering Algorithms to Large Databases (1998) P.S. Bradley, Usama Fayyad, Cory Reina Knowledge Discovery and Data Mining
  • CLARANS: A Method for Clustering Objects for Spatial Data Mining Raymond T. Ng, Jiawei Han
  • BIRCH: An Efficient Data Clustering Method for Very Large Databases (1996) Tian Zhang, Raghu Ramakrishnan, Miron Livny
  • CURE: An efficient clustering algorithm for large databases Sudipto Guha , Rajeev Rastogi , and Kyuseok Shim
  • CHAMELEON: A Hierarchical Clustering Algorithm Using Dynamic Modeling George Karypis, Eui-Hong (Sam) Han, Vipin Kumar
5. Consensus Clustering
   
• Slides Consensus Clustering
  
6. Clustering for sequential and graph data
• Slides Clustering sequential and structured data
7. Semi supervised Clustering
• Introduction to semi supervised Clustering
  • S. Basu, A. Banerjee, R. Mooney,"semi-supervised clustering by seeding"  , ICML-2002
    
  • S. Basu, M. Bilenko, R. Mooney,"A probabilistic framework for semi-supervised clustering", 10th ACM SIGKDD 2004
  • D. Cohn, R. Caruana, A. McCallum, "Semi-supervised Clustering with user feedback", TR2003-1892, Cornell University, 2003