Overview:
The training is aimed at people who want to learn the basics of neural networks and their applications.
Audience:
Anyone interested in Neural Networks.
Pre-Requisite:
Good understanding of mathematics.
Good understanding of basic statistics.
Basic programming skills are not required but recommended.
Course Curriculum
| Introduction and ANN Structure | |||
| Biological neurons and artificial neurons Details | 00:00:00 | ||
| Model of an ANN Details | 00:00:00 | ||
| Activation functions used in ANNs Details | 00:00:00 | ||
| Typical classes of network architectures Details | 00:00:00 | ||
| Mathematical Foundations and Learning mechanisms | |||
| Re-visiting vector and matrix algebra. Details | 00:00:00 | ||
| State-space concepts. Details | 00:00:00 | ||
| Concepts of optimisation. Details | 00:00:00 | ||
| Error-correction learning Details | 00:00:00 | ||
| Memory-based learning Details | 00:00:00 | ||
| Hebbian learning Details | 00:00:00 | ||
| Competitive learning Details | 00:00:00 | ||
| Single layer perceptrons | |||
| Structure and learning of perceptrons Details | 00:00:00 | ||
| Pattern classifier – introduction and Bayes’ classifiers Details | 00:00:00 | ||
| Perceptron as a pattern classifier Details | 00:00:00 | ||
| Perceptron convergence Details | 00:00:00 | ||
| Limitations of a perceptrons Details | 00:00:00 | ||
| Feedforward ANN | |||
| Structures of Multi-layer feedforward networks Details | 00:00:00 | ||
| Back propagation algorithm Details | 00:00:00 | ||
| Back propagation – training and convergence Details | 00:00:00 | ||
| Functional approximation with back propagation Details | 00:00:00 | ||
| Practical and design issues of back propagation learning Details | 00:00:00 | ||
| Radial Basis Function Networks | |||
| Pattern separability and interpolation Details | 00:00:00 | ||
| Regularisation Theory Details | 00:00:00 | ||
| Regularisation and RBF networks Details | 00:00:00 | ||
| RBF network design and training Details | 00:00:00 | ||
| Approximation properties of RBF Details | 00:00:00 | ||
| Competitive Learning and Self organising ANN | |||
| General clustering procedures Details | 00:00:00 | ||
| Learning Vector Quantisation (LVQ). Details | 00:00:00 | ||
| Competitive learning algorithms and architectures Details | 00:00:00 | ||
| Self organising feature maps Details | 00:00:00 | ||
| Properties of feature maps Details | 00:00:00 | ||
| Fuzzy Neural Networks | |||
| Neuro-fuzzy systems Details | 00:00:00 | ||
| Background of fuzzy sets and logic Details | 00:00:00 | ||
| Design of fuzzy stems Details | 00:00:00 | ||
| Design of fuzzy ANNs Details | 00:00:00 | ||
| Applications | |||
| A few examples of Neural Network applications, their advantages and problems will be discussed. Details | 00:00:00 | ||
Course Reviews
No Reviews found for this course.
0 STUDENTS ENROLLED