Neural Network

This course provides an introduction to key concepts and algorithms for neural networks, with strong emphasis on deep learning and its applications. Topics include classical neural networks, statistical pattern recognition, linear models, learning rules, network topologies, multilayer perceptron and backpropagation, deep learning, supervised, unsupervised and reinforcement learning, convolutional networks, recurrent neural networks, algorithms for training deep networks, deep learning to image recognition, computer vision, language modeling. The course consists of weekly lecture, assignments, selected paper presentation and written exam.

Upon the successful completion of this course, students should be able to:

• learn basic neural network architecture.
• learn basic learning algorithms.
• understand the learning and generalization issue in neural computation.
• describe the relation between real brains and simple artificial neural network models.
• apply the popular neural network training methods and learning algorithms for real world applications areas like image classification, recognition of speakers in communications, diagnosis of hepatitis, handwritten word recognition and facial recognition.

Textbooks:

1. The Essence of Neural Networks – Robert Callan, Southampton Institute
2. Neural Networks A Comprehensive Foundation, Simon Haykin, McMaster University, Hamilton, Ontario, Canada, Second Edition

References:

1. Neural Networks and Learning Machines, Third Edition, Simon Haykin, McMaster University, Hamilton, Ontario, Canada
2. An introduction to neural network, Kevin Gurney, University of Sheffield, ISBN 0-203-45151-1 Master e-book ISBN, 2014