Course Outline
DAY 1 - ARTIFICIAL NEURAL NETWORKS
Introduction and ANN Structure.
- Comparison of biological and artificial neurons.
- The modeling of ANNs.
- Activation functions utilized in ANNs.
- Common categories of network architectures.
Mathematical Foundations and Learning mechanisms.
- Review of vector and matrix algebra.
- Concepts in state-space analysis.
- Principles of optimization.
- Error-correction learning.
- Memory-based learning.
- Hebbian learning.
- Competitive learning.
Single layer perceptrons.
- Architecture and training of perceptrons.
- Introduction to pattern classifiers and Bayes' classifiers.
- Using perceptrons as pattern classifiers.
- Perceptron convergence theory.
- Constraints and limitations of perceptrons.
Feedforward ANN.
- Structure of Multi-layer feedforward networks.
- The Back propagation algorithm.
- Training and convergence in back propagation.
- Functional approximation using back propagation.
- Practical considerations and design challenges in back propagation learning.
Radial Basis Function Networks.
- Pattern separability and interpolation techniques.
- Regularization Theory.
- The role of Regularization in RBF networks.
- Design and training of RBF networks.
- Approximation characteristics of RBFs.
Competitive Learning and Self organizing ANN.
- General procedures for clustering.
- Learning Vector Quantization (LVQ).
- Algorithms and architectures for competitive learning.
- Self organizing feature maps.
- Key properties of feature maps.
Fuzzy Neural Networks.
- Neuro-fuzzy systems.
- Foundations of fuzzy sets and logic.
- Designing fuzzy systems.
- Designing fuzzy ANNs.
Applications
- A discussion on several Neural Network applications, highlighting 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
- Rademacher Complexity and VC Dimension
- Bias-Variance tradeoff
- Regularization
- 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 module is taught in conjunction with 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
Requirements
A solid grasp of mathematics is essential.
A strong understanding of basic statistics is required.
While basic programming skills are not mandatory, they are highly recommended.
Testimonials (2)
Working from first principles in a focused way, and moving to applying case studies within the same day
Maggie Webb - Department of Jobs, Regions, and Precincts
Course - Artificial Neural Networks, Machine Learning, Deep Thinking
It was very interactive and more relaxed and informal than expected. We covered lots of topics in the time and the trainer was always receptive to talking more in detail or more generally about the topics and how they were related. I feel the training has given me the tools to continue learning as opposed to it being a one off session where learning stops once you've finished which is very important given the scale and complexity of the topic.
