Course Synopsis
Neural networks is a computational and engineering methodology based on emulating how nature has implemented biological brain (in particular, the brain's massively parallel and learning aspects). As such, it holds promise for significant impact on how important classes of scientific and engineering problems are solved. Neural networks is an adaptable system that approximates the operation of the human brain and the central nervous system. A neural network usually involves a large number of processors operating in parallel, each with its own small sphere of knowledge and access to data in its local memory. Neural Networks can learn from noisy data and generalize on unseen data to provide a very powerful machine learning paradigm. Current applications of neural networks include: oil exploration data analysis, weather prediction, pattern recognition, the interpretation of nucleotide sequences in biology labs, the exploration of models of thinking and consciousness in addition to many other applications.
Course Objectives
This is a hands-on application course that provide step-by-step description while concentrating on useful tips and tricks to construct Neural Network, fundamentals and its applications.
Course Duration
2 Full Days
Who Must Attend
Researchers, Lecturers, Scientists, Engineers and Managers that are keen to use artificial neural network for your application. This hands-on application course with case studies is designed for Scilab users who intend to use Scilab in the areas of Neural Network.
Prerequisites
Candidates must have experience with basic computer operation. Preferably attended our Numerical Computation with SCILAB course.
Course Outline
Introduction
- Definition of neural network
- Biological perspective of neural network
- Neural network applications
- Simple neuron model
- Components of simple neuron
- SCILAB representation of neural network
- Single neuron model
- Neural network with single-layer of neurons
- Neural network with multiple-layer of neurons
Perceptrons
- Introduction
- The perceptron architecture
- Training of perceptrons
- Application examples
Linear Networks
- Introduction
- Architecture of linear networks
- The Widrow-Hoff learning algorithm
- Backpropagation Networks
Backpropagation Networks
- Introduction
- Architecture of backpropagation network
- The backpropagation algorithm
- Training algorithms
- Pre- and post-processing
- Application examples
Self-Organizing Maps
- Introduction
- Competitive learning
- Self-organizing maps
- Application examples