A practical training workshop on the concepts, theories, and implementations of machine learning techniques and tools for applying to real-world problems. Topics include an introduction to data science and machine learning, traditional machine learning techniques, statistical pattern recognition approaches in machine learning, and artificial neural networks, with an overview of deep learning techniques.

PREREQUISITE : Basic Python or programming skills, and Basic mathematics + statistics (if any)

Lesson 1 Data Science & Machine Learning (6 hours)
  1.1. Types & anatomy of data
  1.2. Exploring data
  1.3. Data filtering & transformation
  1.4. Dimensionality reduction
Lesson 2 Traditional Machine Learning Techniques (6 hours)
  2.1. Concept learning & inductive learning hypothesis
  2.2. Decision tree learning
  2.3. Bayesian learning
  2.4. Nearest-neighbours algorithms
Lesson 3 Statistical Pattern Recognition (6 hours)
  3.1. Radial basis functions & kernel-based approaches
  3.2. Support vector machines
  3.3. Cluster analysis & unsupervised learning
  3.4. Linear models & regression problems
Lesson 4 Artificial Neural Networks (6 hours)
  4.1. Perceptrons
  4.2. Stochastic gradient descent algorithm
  4.3. Backpropagation & multi-layered networks
  4.4. Deep learning architectures & applications