DATA425-23S1 (C) Semester One 2023

Foundations of Deep Learning

15 points

Details:
Start Date: Monday, 20 February 2023
End Date: Sunday, 25 June 2023
Withdrawal Dates
Last Day to withdraw from this course:
  • Without financial penalty (full fee refund): Sunday, 5 March 2023
  • Without academic penalty (including no fee refund): Sunday, 14 May 2023

Description

The aim of this course is to introduce students to foundational concepts of deep neural networks. The focus of this course is on both fundamental and applied methods in deep neural networks. A range of topics from convolutional and recurrent type networks to neural-network generative models and attention mechanisms will be introduced.

Learning Outcomes

  • Understand concepts of mathematical foundations of deep learning such as empirical risk minimisation, convergence rates and capacity.
  • Show competency in techniques used in deep neural network model optimisation and analysis. Demonstrate theoretical knowledge of principles governing success of deep learning methods in practise
  • Demonstrate knowledge in designing and analysis of deep neural network models.
  • Be able to undertake a research project involving deep neural networks.

Prerequisites

Subject to HoS approval

Restrictions

Course Coordinator

Varvara Vetrova

Assessment

Assessment Due Date Percentage  Description
Theoretical foundations 20% Theoretical foundations
Reproducibility study 20% Reproducibility study
Review of research paper 20% Review of research paper
Exam 40% Exam

Indicative Fees

Domestic fee $1,079.00

* All fees are inclusive of NZ GST or any equivalent overseas tax, and do not include any programme level discount or additional course-related expenses.

For further information see Mathematics and Statistics .

All DATA425 Occurrences

  • DATA425-23S1 (C) Semester One 2023
Previous year Next year