Neural Network and Deep Learning

In this unit, some of the most widely used prediction and classification models will be covered. A suitable software environment for business analytics will be used, and tools for handling large data sets will be introduced. Neural networks will be introduced to demonstrate  how training can be achieved with backpropagation. Various forms of deep neural networks will be examined, for example multilayer perceptions, convolutional neural networks and recurrent neural networks. The mathematics of stochastic optimisation is used to explain the behaviour and training of these networks. Various programming approaches will be discussed and demonstrated for the training and deployment of neural networks. Deep learning technologies and design examples will be discussed in areas such as face recognition, speech recognition and personal cognitive assistants.