Course coordinator
Dr Thomas Magor
Course overview
- Study period
- Semester 2, 2024 (22/07/2024 - 18/11/2024)
- Study level
- Undergraduate
- Location
- St Lucia
- Attendance mode
- In Person
- Units
- 2
- Administrative campus
- St Lucia
- Coordinating unit
- Business School
Businesses are increasingly finding application of artificial intelligence (AI) to their business processes, offerings, and strategies. Application areas include content recommendation and fraud detection systems, image detection and object classification, personalisation, and self-driving cars. Recent developments in artificial neural networks - referred to as "deep learning" - have made these applications possible. This course provides students with an in-depth exposure to the theory and models of deep learning, with an emphasis on artificial neural networks. These developments extend and greatly improve the predictive accuracy of the traditional machine learning models of predictive analytics. Furthermore, the course provides instruction on software for implementing deep learning models with reference to business and wider applications.
Increasingly, businesses are pursuing impactful and productive applications of AI to their business processes, offerings, and strategies. Examples include Netflix’s content recommendation system, Danske Bank’s fraud detection system, and Facebook’s use of image detection and object classification, Burberry’s approach to personalisation, and Google’s self-driving car initiative. All these applications have been made possible by recent and significant breakthroughs in artificial intelligence. Briefly, the methods of machine learning are the traditional cornerstone of predictive analysis. These methods, and especially recent applications of artificial neural networks have led to the development of deep learning and the emergence of “smart” AI (broadly defined as unsupervised learning). The purpose of thisﾠcourse is to provide students withﾠin-depth coverage of the methods and models of deep learning, with an emphasis on recent advances in the application of artificial neural networks (including the use of estimation software).
In this course, students will learn the fundamentals of deep learning and gain hands-on experience with Convolutional Neural Networks (CNNs) using Keras with TensorFlow. They then apply their knowledge to real-world problems such as object identification, classification, and movement prediction for self-driving cars. Students also explore data augmentation techniques to deal with training data shortages and delve into fraud detection with Autoencoders. Towards the end of the course, students learn about Natural Language Processing and apply their knowledge to text generation using Recurrent Neural Networks (RNNs) and sentiment analysis with word embeddings. R programming language will be used for this course.
Course requirements
Prerequisites
You'll need to complete the following courses before enrolling in this one:
(BISM2201 + 2204) or (BSAN2201 + 2204)
Incompatible
You can't enrol in this course if you've already completed the following:
BISM3212
Course contact
Lecturer
Dr Andrew Jones
Course staff
Tutor
Mr Carlos Rincon Hurtado
Mr David Goyeneche Ramirez
Timetable
The timetable for this course is available on the UQ Public Timetable.
Additional timetable information
Please note: Teaching staff do not have access to the timetabling system to help with class allocation. Therefore, should you need help with your timetable and/or allocation of classes, please ensure you email business.mytimetable@uq.edu.au from your UQ student email account with the following details:
Full Name
Student ID
Course Code
Aims and outcomes
The broad aim of the course BSAN3212 Deep Learning for Business is to provide students with in-depth exposure to the theory and models of deep learning, with an emphasis on artificial neural networks as they apply to business. The course involves instruction in using R, open-source numerical analysis software. The R software has several advanced “packages” for estimating deep learning models as well as allowing users to write theirﾠcode for estimating these models. The course is organised into four modules: (i) preparation for deep learning, (ii) neuro networks, (iii) deep learning projects, and (iv) natural language processing. The more general goals of the course are to learn the language of deep learning, develop an understanding of the key concepts in the application of deep learning, develop an appreciation of the application of deep learning to business, and develop an awareness of the policy and strategy implications of deep learning for business and beyond. The course provides a context in which students can further develop their understanding of the R environment with a view towards becoming effective and professional business analysts.
Learning outcomes
After successfully completing this course you should be able to:
LO1.
Understand the basic concepts of deep learning and AI and explain their relationship to and application in business.
LO2.
Apply the methods of deep learning available in the R software environment with an emphasis on artificial neural networks.
LO3.
Compare and critically evaluate the various approaches to artificial neural networks and assess their value for decision making.
LO4.
Develop an understanding of how deep learning will change business, government, and society, and the associated costs and benefits.
Assessment
Assessment summary
| Category | Assessment task | Weight | Due date |
|---|---|---|---|
| Essay/ Critique | Deep Learning for Business Essay (A1) | 20% |
16/08/2024 4:00 pm |
| Computer Code, Notebook/ Logbook | Deep Learning Coding Project Journal (A2) | 50% |
20/09/2024 4:00 pm |
| Paper/ Report/ Annotation | Deep Learning Project Proposal (A3) | 30% |
18/10/2024 4:00 pm |
Assessment details
Deep Learning for Business Essay (A1)
- Mode
- Written
- Category
- Essay/ Critique
- Weight
- 20%
- Due date
16/08/2024 4:00 pm
- Learning outcomes
- L01, L04
Task description
The use of deep learning methods and increasingly being adopted across various sectors of the economy, and as a result, business and society are likely to undergo significant changes.
In a 2000-word essay, explore how business and society are likely to respond to these changes and what adaptations they may need to make to thrive in this new environment. Consider both the potential benefits and challenges of deep learning and the ethical considerations that must be considered. In your essay, provide specific examples of how deep learning is currently being used in various industries and speculate on how these applications may evolve in the future.
This assessment task evaluates students' abilities, skills, and knowledge without the aid of generative Artificial Intelligence (AI). Students are advised that the use of AI technologies to develop responses is strictly prohibited and may constitute student misconduct under the Student Code of Conduct.
Submission guidelines
Submit via link on BlackBoard
Deferral or extension
You may be able to apply for an extension.
Late submission
A penalty of 10% of the maximum possible mark will be deducted per 24 hours from time submission is due for up to 7 days. After 7 days, you will receive a mark of 0.
Deep Learning Coding Project Journal (A2)
- Mode
- Written
- Category
- Computer Code, Notebook/ Logbook
- Weight
- 50%
- Due date
20/09/2024 4:00 pm
- Learning outcomes
- L01, L02, L03, L04
Task description
As you complete the five in-class deep learning projects, you are asked to produce a coding project journal that details your experience completing two projects of your choice. Your journal should include the following sections:
1. Introduction: Provide an overview of the two projects, including a brief description of the goals of each project and why they are best suited to be addressed using deep learning.
2. Methodology: Describe the process you followed to complete the projects. This should include the tools and techniques you used, any challenges you faced, and how you overcame them.
3. Results: Present the results of your work, including any graphs, charts, or other visualisations that help to convey your findings. Explain how your results contribute to a better understanding of the project goals and deep learning in general.
4. Future projects: Reflect on your experience completing the tasks, including what you learned and how you might apply that knowledge in the future. Consider any limitations or caveats to your work and how they might impact the conclusions you drew. Summarise the key takeaways from completing the projects and speculate on how the methodologies could be applied to an important business problem.
This assessment task evaluates students' abilities, skills, and knowledge without the aid of generative Artificial Intelligence (AI). Students are advised that the use of AI technologies to develop responses is strictly prohibited and may constitute student misconduct under the Student Code of Conduct.
Submission guidelines
Submit via link on BlackBoard
Deferral or extension
You may be able to apply for an extension.
Late submission
A penalty of 10% of the maximum possible mark will be deducted per 24 hours from time submission is due for up to 7 days. After 7 days, you will receive a mark of 0.
Deep Learning Project Proposal (A3)
- Mode
- Written
- Category
- Paper/ Report/ Annotation
- Weight
- 30%
- Due date
18/10/2024 4:00 pm
- Learning outcomes
- L01, L02, L03, L04
Task description
Building upon the ideas and concepts explored in your first essay and journal documenting your completion of two in-class deep learning projects, you will now propose a deep learning project of your own. In a 3000-word project proposal, you should aim to address a significant business challenge or opportunity within a specific industry or field that can be tackled using deep learning methods.
Your project proposal should include the following sections:
- Introduction: Provide a brief overview of the challenge or opportunity you will be addressing with your proposed project. Explain why this challenge or opportunity is significant and why deep learning methods are well-suited to address it.
- Project Objectives: Define the specific objectives of your project. This should include a clear statement of the problem you will be addressing and the goals you hope to achieve with your deep learning solution.
- Methodology: Describe the deep learning methods you will use to achieve your project objectives. This should include a clear explanation of the algorithms, models, and techniques you will be employing and any data sources you will be using.
- Evaluation: Define the evaluation metrics you will use to assess the effectiveness of your deep learning solution. This should include both quantitative and qualitative metrics, as appropriate.
- Timeline: Provide a detailed timeline for completing your proposed project. This should include specific milestones and deadlines for each phase of the project and any potential roadblocks or challenges you anticipate.
- Conclusion: Summarise your project proposal, including its objectives, methodology, evaluation metrics, and timeline. Discuss the potential impact of your proposed project and how it may contribute to the broader field of deep learning.
This assessment task evaluates students' abilities, skills, and knowledge without the aid of generative Artificial Intelligence (AI). Students are advised that the use of AI technologies to develop responses is strictly prohibited and may constitute student misconduct under the Student Code of Conduct.
Submission guidelines
Submit via link on BlackBoard
Deferral or extension
You may be able to apply for an extension.
Late submission
A penalty of 10% of the maximum possible mark will be deducted per 24 hours from time submission is due for up to 7 days. After 7 days, you will receive a mark of 0.
Course grading
Full criteria for each grade is available in the Assessment Procedure.
| Grade | Cut off Percent | Description |
|---|---|---|
| 1 (Low Fail) | 0 - 29 |
Absence of evidence of achievement of course learning outcomes. |
| 2 (Fail) | 30 - 46 |
Minimal evidence of achievement of course learning outcomes. |
| 3 (Marginal Fail) | 47 - 49 |
Demonstrated evidence of developing achievement of course learning outcomes |
| 4 (Pass) | 50 - 64 |
Demonstrated evidence of functional achievement of course learning outcomes. |
| 5 (Credit) | 65 - 74 |
Demonstrated evidence of proficient achievement of course learning outcomes. |
| 6 (Distinction) | 75 - 84 |
Demonstrated evidence of advanced achievement of course learning outcomes. |
| 7 (High Distinction) | 85 - 100 |
Demonstrated evidence of exceptional achievement of course learning outcomes. |
Additional course grading information
Grades will be allocated according to University-wide standards of criterion-based assessment.
Supplementary assessment
Supplementary assessment is available for this course.
Learning resources
You'll need the following resources to successfully complete the course. We've indicated below if you need a personal copy of the reading materials or your own item.
Library resources
Find the required and recommended resources for this course on the UQ Library website.
Learning activities
The learning activities for this course are outlined below. Learn more about the learning outcomes that apply to this course.
Filter activity type by
Please select
| Learning period | Activity type | Topic |
|---|---|---|
Week 1 |
Seminar |
Course introduction and A1 overview Learning outcomes: L01, L04 |
Week 2 |
Seminar |
Preparation for Deep Learning Learning outcomes: L01, L02 |
Week 3 |
Seminar |
Neural Networks Learning outcomes: L01, L02, L03, L04 |
Week 4 |
No student involvement (Breaks, information) |
EKKA Public Holiday |
Week 5 |
Seminar |
Concurrent Neural Networks (CNNs) Learning outcomes: L02, L03 |
Week 6 |
Seminar |
Autoencoders Learning outcomes: L02, L03 |
Week 7 |
Seminar |
Recurrent Neural Networks (RNNs) Learning outcomes: L02, L03 |
Week 8 |
Seminar |
Text Analytics Learning outcomes: L02, L03 |
Week 9 |
Seminar |
Reviewing the Fundamentals of Deep Learning Learning outcomes: L01, L02, L03, L04 |
Mid Sem break |
No student involvement (Breaks, information) |
In-semester Break |
Week 10 |
Seminar |
Deep Learning Project Proposal (A3) briefing Learning outcomes: L02, L03 |
Week 11 |
Seminar |
Generative AI and other real world applications Learning outcomes: L01, L03, L04 |
Week 12 |
Seminar |
Deep Learning Project (A3) finalisation workshop Learning outcomes: L02, L03, L04 |
Week 13 |
Seminar |
Course Review and Recap Learning outcomes: L01, L02, L03, L04 |
Policies and procedures
University policies and procedures apply to all aspects of student life. As a UQ student, you must comply with University-wide and program-specific requirements, including the:
- Student Code of Conduct Policy
- Student Integrity and Misconduct Policy and Procedure
- Assessment Procedure
- Examinations Procedure
- Reasonable Adjustments - Students Policy and Procedure
Learn more about UQ policies on my.UQ and the Policy and Procedure Library.