Deep learning is currently the central machine learning method fueling the artificial intelligence revolution. In this subject you will learn how to apply deep learning algorithms to solve real-world computer vision and natural language processing problems. This subject does not assume you have previous machine learning experience, therefore it starts … For more content click the Read more button below.
Deep learning is currently the central machine learning method fueling the artificial intelligence revolution. In this subject you will learn how to apply deep learning algorithms to solve real-world computer vision and natural language processing problems. This subject does not assume you have previous machine learning experience, therefore it starts teaching deep learning at a very introductory level. You will learn how deep learning techniques can be applied to tasks such as image recognition, sentiment classification, machine translation, question and answering, speech synthesis, etc. The practical skills taught in this subject will allow you to build production level deep learning software that can scale out to millions of users. You will be introduced to the popular deep learning programming framework of Pytorch and popular model architectures such as convolutional, recurrent and transformer neural networks.
Capstones provide students with a way of integrating and applying knowledge and skills gained throughout their course.
Yes
Academic progress review - Schedule A subject
No
Subject instances
To view instance specific details which include - Assessments, Class requirements and Subject instance coordinators - please select your preferred instance via the drop-down menu at the top right-hand side of this page.
Learning resources
Recommended - Other resource - Deep Learning
Title:Deep Learning
Resource requirement:Recommended
Author/editor:Ian Goodfellow and Yoshua Bengio and Aaron Courville
Year:2016
Publisher:MIT Press
Career ready
Work based learning (placement):No
Graduate capabilities
COMMUNICATION - Digital Capability
DISCIPLINE KNOWLEDGE AND SKILLS
INQUIRY AND ANALYSIS - Critical Thinking and Problem Solving
INQUIRY AND ANALYSIS - Research and Evidence-Based Inquiry
PERSONAL AND PROFESSIONAL - Ethical and Social Responsibility
Subject intended learning outcomes
On successful completion you will be able to:
1.
Analyse the advantages and disadvantages of using traditional machine learning algorithms versus deep learning algorithms for solving industry problems.
2.
Analyse a given industry problem and then investigate which deep learning algorithm best solves the problem.
3.
Write PyTorch code to implement deep learning algorithms to solve computer vision and natural language processing problems.
4.
Analyse the machine learning requirements of a business and then propose deployment and maintenance strategies for deep learning production systems in the cloud.
5.
Given a real-world problem where labels are scarce, investigate different deep-learning approaches to tackle this problem. Approaches include transfer learning, semi-supervised learning, unsupervised pre-training, etc.
