Artificial Neural Networks, Machine Learning, Deep Thinking Training Course

DAY 1 - ARTIFICIAL NEURAL NETWORKS

Introduction and ANN Structure.

• Comparison of biological and artificial neurons.
• The ANN model.
• Activation functions employed in ANNs.
• Common network architecture classes.

Mathematical Foundations and Learning mechanisms.

• Refresher on vector and matrix algebra.
• State-space concepts.
• Optimization concepts.
• Error-correction learning.
• Memory-based learning.
• Hebbian learning.
• Competitive learning.

Single layer perceptrons.

• Perceptron structure and learning process.
• Pattern classifier - introduction and Bayes' classifiers.
• Using the Perceptron as a pattern classifier.
• Perceptron convergence.
• Limitations of perceptrons.

Feedforward ANN.

• Architecture of Multi-layer feedforward networks.
• The Back propagation algorithm.
• Back propagation - training and convergence.
• Functional approximation via back propagation.
• Practical and design challenges in back propagation learning.

Radial Basis Function Networks.

• Pattern separability and interpolation.
• Regularization Theory.
• Regularization in RBF networks.
• Design and training of RBF networks.
• Approximation capabilities of RBF.

Competitive Learning and Self organizing ANN.

• General clustering methods.
• Learning Vector Quantization (LVQ).
• Competitive learning algorithms and architectures.
• Self-organizing feature maps.
• Attributes of feature maps.

Fuzzy Neural Networks.

• Neuro-fuzzy systems.
• Foundations of fuzzy sets and logic.
• Design of fuzzy stems.
• Design of fuzzy ANNs.

Applications

• Discussion of several Neural Network application examples, including their benefits and challenges.

DAY -2 MACHINE LEARNING

• The PAC Learning Framework
  • Guarantees for finite hypothesis sets – consistent case
  • Guarantees for finite hypothesis sets – inconsistent case
  • Generalities
    • Deterministic vs. Stochastic scenarios
    • Bayes error noise
    • Estimation and approximation errors
    • Model selection
• Radecher Complexity and VC – Dimension
• Bias - Variance tradeoff
• Regularisation
• Over-fitting
• Validation
• Support Vector Machines
• Kriging (Gaussian Process regression)
• PCA and Kernel PCA
• Self Organisation Maps (SOM)
• Kernel induced vector space
  • Mercer Kernels and Kernel - induced similarity metrics
• Reinforcement Learning

DAY 3 - DEEP LEARNING

This session will build upon the topics covered on Day 1 and Day 2

• Logistic and Softmax Regression
• Sparse Autoencoders
• Vectorization, PCA and Whitening
• Self-Taught Learning
• Deep Networks
• Linear Decoders
• Convolution and Pooling
• Sparse Coding
• Independent Component Analysis
• Canonical Correlation Analysis
• Demos and Applications