Unit Description and General Aims

This unit explores aspects of Artificial Intelligence and Data Science using computer science programming language such as Python. Machine learning and data science, as tools for artificial intelligence, are some of the most widely adopted scientific fields. The purpose of this unit is to provide the most important aspects of artificial intelligence and machine learning by presenting series of comprehensive yet simple lectures and tutorials using Python programming language. This unit includes hands-on guiding lectures with practical case studies of data analysis problems effectively. Students will learn data analysis, regressions, clustering, neural networking, etc. by using pandas, NumPy, IPython, and Jupiter in the Process.

Learning Outcomes

On successful completion of this Unit, students are expected to be able to:

1. Explain data analysis models, and their advantages and disadvantages.
   Bloom’s Level 2
2. Analyse datasets with the machine learning techniques.
   Bloom’s Level 4
3. Analyse datasets with the concepts of deep learning and artificial neural networks.
   Bloom’s Level 4
4. Write scripts and applications for the analysis of streaming data.
   Bloom’s Level 4
5. Evaluate the advantages and disadvantages of deep learning neural network architectures.
   Bloom’s Level 5
6. Explain how to develop AI systems to meet business, organizational, and technology requirements.
   Bloom’s Level 6
7. Solve real-world problems in organizational processes and workflows by applying critical thinking, problem-solving, and cognitive computing skills.
   Bloom’s Level 6

Student assessment

Overall requirements: Students must achieve a result of 50% or above in the exam itself to pass the exam and must pass the exam to be able to pass the unit. An overall final unit score of 50% or above must be achieved to pass the unit once all assessment, including the exam, has been completed.

Prescribed and Recommended Readings

Textbook:

• A. Subasi, Elsevier 2020, Practical Machine Learning for Data Analysis Using Python, ISBN 978-0-12-821379-7. Online version available at: 
• Jake VanderPlas, O'Reilly Media, Inc. 2022, Python Data Science Handbook, 2nd Edition, ISBN: 978-1-491-91205-8

Reference:

• Vlayutham, Sathiyamoorthi, IGI Global 2020, Handbook of Research on Application and Implementations of Machine Learning Techniques, ISBN 978-1-5225-9902-9. Online version available at: 
• Alex Galea, 2018, Beginning Data Science with Python and Jupyter, Packt Publishing Ltd. ISBN 978-1-78953-202-9.
• Brian Heinold, 2012, A Practical Introduction to Python Programming, Department of Mathematics and Computer Science Mount St. Mary’s University.
• Rashid Khan, Anik Das, 2018, Build Better Chatbots, A Complete Guide to Getting Started with Chatbots, Springer, ISBN-13 (electronic): 978-1-4842-3111-1. https://doi.org/10.1007/978-1-4842-3111-1

Notes and Reference texts:

• Knovel library: http://app.knovel.com
• IDC notes and Reference texts as advised
• Other material advised during the lectures

Unit Content

One topic is delivered per contact week, with the exception of part-time 24-week units, where one topic is delivered every two weeks.

Topic 1

Python and Data Science Basics Quick Review

• Data types, Strings, Lists, Dictionaries
• Flow control and loops
• Conditional statements, objects, classes, plots
• Python vs R
• Data Analysis vs Data Science vs Machine Learning

Topic 2

Data Processing and Visualization

• Working with Jupyter notebooks, Pandas, NumPy
• Processing data, texts, and csv files
• Feature selection from data
• Processing information from online and internal data sources
• Goal and objectives of visualization
• Visualization with Matplotlib and pycharts

Topic 3

Introduction to Machine Learning

• Linear regression
• Overfitting and underfitting
• Regularization
• Cross-validation
• Developing a machine learning model
• Applications of Data Mining

Topic 4

Supervised Machine Learning

• Decision trees
• K-Nearest neighbors
• Naïve bayes
• Logistic regression
• Support vector machines

Topic 5

Unsupervised Machine Learning

• Clustering
• Principal components analysis
• Neural network overview
• Convolutional neural networks
• Autoencoders
• Recurrent neural networks

Topic 6

Search with Artificial Intelligence (AI)

• Finding the best route from origin to destination
• Agents, state, actions
• Transition model as a function
• State space by sequence of actions and directed graphs
• Goal tests and path costs

Topic 7

Knowledge and Conclusions in AI

• Knowledge-based agents and sentences
• Propositional logics and symbols
• Logic connectives, Implication, Biconditional
• Knowledge-based models
• Inference and knowledge engineering
• Modus ponens, elimination, double negation, De Morgan’s law, etc.

Topic 8

AI for Uncertainty and Probability

• Possible worlds scenario and axioms in probability
• Unconditional and conditional probability
• Random variables and independence
• Baye’s rule and joint probability
• Probability rules: Negation, inclusion-exclusion, marginalization
• Bayesian networks, inference, sampling
• Markov’s models, assumptions, and chains

Topic 9

Optimization of AI Algorithms

• Local search
• Hill climbing
• Simulated annealing
• Linear programming and constraint satisfaction
• Node and arc consistencies
• Backtracking search

Topic 10

Neural Networks

• Activation functions
• Neural network structures
• Stochastic and mini-batch gradient descent
• Multilayer neural networks
• Back propagation and overfitting
• Tensor flow

Topic 11

Computer Vision and Image Processing

• Computer vision and image convolution
• Convolutional neural networks
• Deep learning for computer vision
• Image classification and retrieval
• Object detection
• Semantic segmentation

Topic 12

Project and Unit Review

In the final week, students will have an opportunity to review the contents covered so far and will be engaged in practical engagement mini projects. Opportunity will be provided for a review of student work and to clarify any outstanding issues. Instructors/facilitators may choose to cover a specialized topic if applicable to that cohort.

Software/Hardware Used

Software

• Software: Pytorch, KNIME, Apache Mahout, MATLAB

• Version: N/A

• Instructions:  N/A

• Additional resources or files: N/A

Hardware

• N/A

Unit Changes Based on Student Feedback