Skip to main content

Data Mining and Machine Learning UCA

Enrollment in this course is by invitation only

About This Course


Data Mining and Machine Learning techniques have demonstrated their high potential to understand and optimize business, scientific and social activities in recent years. These techniques automatically process very large sets of heterogeneous data, without prior hypotheses or knowledge, to extract patterns describing hidden data properties and deduce models for predicting future events. This course introduces the central concepts and practical considerations of the domain that will be illustrated and implemented using the R software and its large set of available add-ons.

It's the seventh academic course of the master eMBDS.


Course duration and workload


This is a weekly course over 4 weeks.

Each monday, short video sequences will be offered to participants.

MCQs will evaluate the knowledge at the end of each week.

The weekly MCQs will be used to your self trained.

At the end of the 4 weeks, a supervised exam will be proposed to pass the certificate.

Plan to spend 5h per week + 1h of supervised exam are necessary.


Prerequisites


This self-contained course is integral part of the MBDS Master Graduate Program in Computer Science at the university of Nice – Sophia-Antipolis, in France. Suitable for professionals and students.



Syllabus

Data Mining and Machine Learning is organized into 4 weekly modules :

  • MODULE - 1 : Introduction to Data Mining and Machine Learning with the R Software
    • Introduction to the R Software
      • Basics of the R Software and Why this Solution?
      • Central Data Storage Notions for Data Mining and Machine Learning
      • Data Frame Manipulations for Selecting and Modifying Data
      • Development Environments, Online Resources, Add-ons and Documentations
    • Introduction to Data Mining and Machine Learning
      • Data Mining, Machine Learning and Knowledge Discovery from Data
      • Introductive Examples of Unsupervised Learning of Frequent Patterns
      • Introductive Examples of Unsupervised Learning of Similarity Patterns
      • Introductive Examples of Supervised Learning of Predictive Models
  • MODULE - 2 : Supervised Learning of Predictive Knowledge Models
    • What are Supervised Learning and Classification?
    • Supervised Learning of Classifiers
    • Decision Tree Induction Approaches
    • Representations of Decision Trees
    • Confusion Matrix and Evaluation Measures
    • ROC Curve and AUC Index
    • Learning Approaches and Algorithms
    • Conclusion and References
  • MODULE - 3 : Unsupervised Learning of Data Relationship Knowledge Patterns
  • MODULE - 4 : Unsupervised Learning of Instance Similarity Knowledge Patterns


Course Staff

Nicolas PASQUIER

Senior lecturer at the Computer Science Department

Member of the I3S Laboratory

University Côte d'Azur FRANCE



Terms of use

of the course :

Licence Creative Commons BY NC ND : the user must mention the author's name, he may exploit the work except in a commercial context, he can not create a work derived from the original work.

of the content produced by users :

Restrictive license : your production is your intellectual property and can not be reused.

  1. Course Number

    107010
  2. Classes Start

    Jan 27, 2020
  3. Classes End

    Feb 21, 2020
  4. Estimated Effort

    05H00