Artificial Neural Networks, Machine Learning, Deep Thinking Training Course

DAY 1 - ARTIFICIAL NEURAL NETWORKS

Introduction and ANN Architecture.

• Comparison of biological and artificial neurons.
• Theoretical modeling of ANNs.
• Activation functions employed in ANNs.
• Standard classifications of network architectures.

Mathematical Foundations and Learning Mechanisms.

• Review of vector and matrix algebra.
• State-space concepts.
• Optimization principles.
• Error-correction learning methods.
• Memory-based learning approaches.
• Hebbian learning principles.
• Competitive learning strategies.

Single-layer Perceptrons.

• Architecture and training of perceptrons.
• Introduction to pattern classifiers and Bayes' classifiers.
• Application of perceptrons as pattern classifiers.
• Convergence of the perceptron algorithm.
• Constraints and limitations of perceptrons.

Feedforward ANNs.

• Configuration of Multi-layer feedforward networks.
• The Backpropagation algorithm.
• Backpropagation: training processes and convergence.
• Functional approximation via backpropagation.
• Practical considerations and design challenges in backpropagation learning.

Radial Basis Function Networks.

• Pattern separability and interpolation techniques.
• Theory of Regularization.
• Integration of Regularization with RBF networks.
• Design and training of RBF networks.
• Approximation capabilities of RBFs.

Competitive Learning and Self-organizing ANNs.

• General clustering methodologies.
• Learning Vector Quantization (LVQ).
• Algorithms and architectures for competitive learning.
• Self-organizing feature maps.
• Characteristics of feature maps.

Fuzzy Neural Networks.

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

Applications

• Discussion of various Neural Network applications, highlighting their advantages and associated challenges.

DAY 2 - MACHINE LEARNING

• The PAC Learning Framework
  • Guarantees for finite hypothesis sets: the consistent case
  • Guarantees for finite hypothesis sets: the inconsistent case
  • General Principles
    • Deterministic vs. Stochastic scenarios
    • Bayes error noise
    • Estimation and approximation errors
    • Model selection strategies
• Rademacher Complexity and VC Dimension
• Bias-Variance tradeoff
• Regularization techniques
• Overfitting concepts
• Validation methods
• Support Vector Machines
• Kriging (Gaussian Process regression)
• PCA and Kernel PCA
• Self-Organizing Maps (SOM)
• Kernel-induced vector spaces
  • Mercer Kernels and Kernel-induced similarity metrics
• Reinforcement Learning

DAY 3 - DEEP LEARNING

This module builds upon the topics covered in 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 Practical Applications