MDA522 - Artificial Intelligence

Credit Points: 20 credit points

Workload: 60 hours

Prerequisite: MDA512 Data Science

Co-requisite: N/A

Aims & Objectives

This is a core unit out of a total of 12 units in the Master of Data Analytics (MDA). This unit addresses the course learning outcomes and complements other units in a related field by developing students’ specialised knowledge of Artificial Intelligence (AI). For further course information refer to: http://www.mit.edu.au/study-with-us/programs/master-data-analytics. This unit is part of the AQF level 9 (MDA) course.

Students will gain an understanding of AI tools and technologies to learn “hidden” aspects of data, and to interpret this in a useful form. Students will explore machine learning methods and techniques with temporal data, involving different learning mechanisms. Students will have an opportunity to apply their machine learning skills practically onto real-world case studies.

This unit will cover the following topics:

  • Artificial Intelligence (AI) models, techniques, and knowledge representation
  • Building and testing of AI models
  • Managing AI models with best practices in system evaluation
  • Application of machine learning tools and techniques in AI
  • Application of supervised, unsupervised and deep learning in data analytics

Learning Outcomes

4.1 Course Learning Outcomes
The Course learning outcomes applicable to this unit in respect of the course being studied are listed on the Melbourne Institute of Technology website: www.mit.edu.au 
4.2 Unit Learning Outcomes
At the completion of this unit students should be able to:

  1. Apply the key components of Artificial Intelligence (AI) models and techniques.
  2. Evaluate AI algorithms and Machine Learning (ML) models.
  3. Manage and lead development of AI solutions for complex problems.
  4. Compare and analyse the performance of AI techniques in accordance with the industry standard.
  5. Investigate and recommend appropriate artificial neural networks and deep learning solutions for industry applications.
     

Weekly Topics

This unit will cover the content below:

Week # Lecture Topic Laboratory Topics
1 Introduction to AI Exercises on Turing Test Growing job opportunities in AI
2 Intelligent Agents
  • Types of Agents
  • Agents and Environments
Why the focus is on ‘rational’ agent?
https://aimacode.github.io/aima-exercises/agents-exercises/
3 Problem solving I
  • Solving problems by searching (uninformed)
Beyond Classical Search (informed)
Precise problem formulation
BFS and DFS based applications
4 Problem solving II
  • Adversarial search
  • Constraint satisfaction problems
8 puzzles problem solving
Minimax optimality
Multiplayer game
5 Knowledge Reasoning, Planning, Representation
  • First Order logic, Inferences, Planning and acting, Knowledge representation
FoPL related exercises in Python
Inferencing and knowledge representing programs
6 Uncertain knowledge and reasoning Quantifying uncertainty, Probabilistic reasoning, Making simple and complex decisions Decision making exercise and simple python programs to depict decision making.( using code from Git hub)
7

Introductory Machine Learning

  • Examples, Knowledge in learning,
  • Learning probabilistic learning and reinforcement learning
Programs in python to modify the existing programs with additional constrains / requirements
8

Supervised Learning I

  • Bayes Classifiers
  • Decision forest
Design of simple binary classifier using Python Case example of virus detection using machine learning
9

Supervised Learning II

  • Artificial neural network Support vector machine
Design of decision trees using Python Case example of bankruptcy prediction using machine learning
10

Unsupervised Learning

  • Hierarchical K-means clustering Association mining
Design of K-means clustering using Python Case example of social media data clustering and explorations
11

Deep Learning

  • Motivation(s)
  • Categories of approach Example applications
Design of deep belief network in Python Case example of image processing application
12

Review and future trends

  • NLP and Robotics

Future AI methods in data analysis

Data analysis with AI Segmentation of words and similar programs in python

Assessment

Assessment Task Due Date Release Date A B Learning Outcomes Assessed
Assignment 1  Week 3 Week 1 5%   a
In-class test Week 6 Week 1   10% a-b
Assignment 2 Week 11 Week 7 25%   c-d
Laboratory and Problem Based Learning participation & submission Week 2-11 Week 1 10%   a-e
Final Examination (3 hours)       50% a-e
TOTALS     40% 60%  

Task Type: Type A: unsupervised, Type B: supervised.

Contribution and participation (in class) (10%)

This unit has class participation and student contribution as an assessment. The assessment task and marking rubric will follow
the Guidelines on Assessing Class Participation (https://www.mit.edu.au/about-us/governance/institute-rules-policies-andplans/policies-procedures-and-guidelines/Guidelines_on_Assessing_Class_Participation). Further details will be provided in the
assessment specification on the type of assessment tasks and the marking rubrics.
 

Textbook and Reference Materials

Textbook

  • S. Russell, P. Norvig, Artificial Intelligence: A Modern Approach, 4th Ed., Pearson, 2019.
  • S. Raschka, V. Mirjalili, Python Machine Learning, Machine learning and deep learning with Python, scikit-learn and TensorFlow, Packt Publishing, UK, 2nd Ed., 2017.

References

  • M. B. White, Machine Learning: A Journey from Beginner to Advanced Including Deep Learning, Scikit-learn and Tensorflow,  CreateSpace Independent Publishing Platform, 2nd Ed., 2018.
  • C. C. Aggarwal, Neural Networks and Deep Learning, Springers, Switzerland, 1st Ed., 2018.
  • M. Lapan, Deep Reinforcement Learning Hands-On: Apply modern RL methods, with Deep Q-networks, Value Iteration, Policy Gradients, TRPO, AlphaGo Zero, Packt Publishing, UK, 2018.
  • S. Ravichandiran, Hands-On Reinforcement Learning with Python: Master Reinforcement And Deep Reinforcement Learning using OpenAI Gym and TensorFlow, Packt Publishing, UK, 2018.
  • Y. Liu, Python Machine Learning By Example: The Easiest Way to Get Into Machine Learning, Packt Publishing, UK, 2017
  • F. Chollet, Deep Learning with Python, Manning Publications Co., New York, 2018.

Journals

  • IEEE Transactions on Neural Networks and Learning Systems.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence.
  • Foundations and Trends in Machine Learning.
  • Journal of Machine Learning Research.
  • Artificial Intelligence.
  • International Journal of Machine Learning and Cybernetics.
  • International Journal of Artificial Intelligence.
  • Intelligent Data Analysis.
  • Applied Artificial Intelligence.
  • Journal of Experimental and Theoretical Artificial Intelligence.
  • Journal of Artificial Intelligence.

Adopted Reference Style: IEEE

Graduate Attributes

MIT is committed to ensure the course is current, practical and relevant so that graduates are “work ready” and equipped for life-long learning. In order to accomplish this, the MIT Graduate Attributes identify the required knowledge, skills and attributes that prepare students for the industry.
The level to which Graduate Attributes covered in this unit are as follows:

Ability to communicate Independent and Lifelong Learning Ethics Analytical and Problem Solving Cultural and Global Awareness Team work Specialist knowledge of a field of study

Legend

Levels of attainment Extent covered
The attribute is covered by theory and practice, and addressed by assessed activities in which the students always play an active role, e.g. workshops, lab submissions, assignments, demonstrations, tests, examinations.
The attribute is covered by theory or practice, and addressed by assessed activities in which the students mostly play an active role, e.g. discussions, reading, intepreting documents, tests, examinations.
The attribute is discussed in theory or practice; it is addressed by assessed activities in which the students may play an active role, e.g. lectures and discussions, reading, interpretation, workshops, presentations.
The attribute is presented as a side issue in theory or practice; it is not specifically assessed, but it is addressed by activities such as lectures or tutorials.
The attribute is not considered, there is no theory or practice or activities associated with this attribute.