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.

Unit details

Location:
Footscray Park
VU Sydney
Study level:
Postgraduate
Credit points:
12
Unit code:
NIT6004

Prerequisites

NIT5150 - Advanced Object Oriented Programming

Get help

Find a different unit

Learning Outcomes

On successful completion of this unit, students will be able to:
  1. Critically review the performance and applications of neural network and deep learning techniques;  
  2. Implement a systems approach to design and evaluate neural network architecture;  
  3. Interpret mathematical equations from linear algebra, calculus, statistics, and probability theory in terms of neural network architecture and deep learning methods;  
  4. Investigate and apply knowledge discovery processes and associated models to innovate deep learning applications to support and provide business solutions; and  
  5. Extrapolate knowledge and skills to design, develop, and evaluate a variety of deep learning tasks: modelling, clustering, dimensionality reduction, regression and classification.  

Assessment

Assessment type Description Grade
Assignment Assignment 20%
Project Project 40%
Test Open book test (Concepts, modelling, training methods, programming and scenario analysis) 40%
Assignment - Develop and train a neural network that solves simple practical problems, for example big data classification. Project - Advanced application of deep learning technique, for example create a personal cognitive assistant for daily news review.

Where to next?

As part of a course

This unit is studied as part of the following courses. Refer to the course page for information on how to apply for the course.

VU takes care to ensure the accuracy of this unit information, but reserves the right to change or withdraw courses offered at any time. Please check that unit information is current with the Student Contact Centre.