Home Registration Course Details Speakers Details Contacts

INTERACTIVE AND VISUAL APPROACHES TO DATA MINING

October 30 – November 03, 2017

Indian Statistical Institute, 203, B. T. Road, Kolkata-700108

Course Details

Day 1

Lecture 1 by foreign speaker: Introduction to visual programming and data mining workflows. Data input, visualization, data selection and interactive data exploration. Scatter plot visualization, choice of projection.

Tutorial: Hands on tutorial on various data mining tools.

Day 2

Lecture 2 by foreign speaker: Classification. Logistic regression. Classification trees. Confusion matrix. Scoring of classification models. Classification accuracy and AUC. Data sampling, training and test sets. Cross-validation. A glimpse into random forests, SVM and other top-performing algorithms. Statistical comparison of classifiers.

Lecture 3 by foreign speaker: Regression. Linear regression. Regularization. Effects of regularization on training and test sets. Parameter search. Other regression techniques (random forests). Regularization and parameter search in classification.

Day 3

Tutorial : Hands on tutorial on some classifiers.

Lecture 4 by foreign speaker: Clustering. Hierarchical clustering. Explorative data analysis with clustering and data projections. k-means clustering. Time and space complexity. Cluster scoring and selection of number of clusters. Probabilistic clustering.

Day 4

Lecture 5 by foreign speaker: Data projections and networks. Principal component analysis. Multidimensional scaling. Construction, visualization and analysis of correlation networks. Analysis of connectivity. Discovery of hubs and network-based clustering.

Tutorial 3: Hands on tutorial on some clustering methods.

Day 5

Lecture 6 by foreign speaker: Image analysis. Text mining. Embedding. Deep learning.

Lecture 7 by foreign speaker: Course wrap-up. Mining your own data. Pitfalls to avoid.