BEIA513 

Module Name	Data Analytics and Artificial Intelligence
Module Code	BEIA513
Level	Five
Credits	15

Module Description and General Aims 

This module 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 module 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 module 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 Module, students are expected to be able to: 

1. Explain data analysis models, and their advantages and disadvantages. 

Bloom’s Level 1  

2. Analyse datasets with the machine learning techniques. 

Bloom’s Level 2 

3. Analyse datasets with the concepts of deep learning and artificial neural networks. 

Bloom’s Level 3 

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 6 

6. Explain how to develop AI systems to meet business, organizational, and technology requirements.  

Bloom’s Level 5 

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 

Assessment Type	When assessed	Weighting (% of total module marks)	Learning Outcomes Assessed
Assessment 1 Type: Multi-choice test / Group work / Short answer questions / Practical / Remote Lab / Simulation Example Topic: Python data types, loops, objects, and classes. Students may complete a quiz with MCQ type answers and solve some simple equations to demonstrate a good understanding of the fundamental concepts	Due after Topic 3	15%	1, 2
Assessment 2 Type: Multi-choice test / Group work / Short answer questions / Practical / Remote Lab / Simulation Example Topic: Machine learning, data processing, visualization, regression. Students may provide solutions to simple problems on the listed topics	Due after Topic 6	25%	1, 2
Assessment 3 Type: Report (Final Project) [If a continuation of the midterm, this should complete the report by adding sections on: methodology, implementation / evaluation, verification / validation, conclusion / challenges and recommendations / future work. If this is a new report, all headings from the midterm and the final reports must be included.] Word length: 2000 Topic examples: AI methods, applications, and algorithms.	Due after Topic 9	20%	3, 4, 5
Assessment 4 Type: May be in the form of quizzes, class tests, practical assessments, remote labs, simulation software or case studies Examples: Create new applications using Machine Learning, Deep Learning, and Computer Vision. Create forecasting analysis using AI tools and predict future orders. Automatically make standalone web documents and presentations using Python Bokeh.	Final Week	40%	All
Tutorial Attendance & Participation            Description: Attendance, presentation, discussion, group work, exercises, self-assessment/reflection, case study analysis, application.	Continuous	5%	All

Prescribed and Recommended Readings  

Textbook 

• Subasi, Abdulhamit, Elsevier 2020, Practical Machine Learning for Data Analysis Using Python, ISBN 978-0-12-821379-7. Online version available at: http://app.knovel.com/hotlink/toc/id:kpOMLDAUP1/practical-machine-learning/practical-machine-learning 

• Peters Morgan, AI Sciences 2016, Data Analysis from Scratch with Python, Step by Step Guide, ISBN-13: 978-1721942817.  

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: http://app.knovel.com/hotlink/toc/id:kpHRAIMLT2/handbook-research-applications/handbook-research-applications  

• 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 

Module Content  

One topic is delivered per contact week.  

Topic 1: Python and Data Science Basics Quick Review 

1. Data types, Strings, Lists, Dictionaries 

2. Flow control and loops 

3. Conditional statements, objects, classes, plots 

4. Python vs R 

5. Data Analysis vs Data Science vs Machine Learning 

Topic 2: Data Processing and Visualization 

1. Working with Jupyter notebooks, Pandas, NumPy 

2. Processing data, texts, and csv files 

3. Feature selection from data 

4. Processing information from online and internal data sources 

5. Goal and objectives of visualization 

6. Visualization with Matplotlib and pycharts 

Topic 3: Introduction to Machine Learning 

1. Linear regression 

2. Overfitting and underfitting 

3. Regularization 

4. Cross-validation 

5. Developing a machine learning model 

6. Applications of Data Mining 

Topics 4: Supervised Machine Learning 

1. Decision trees 

2. K-Nearest neighbours 

3. Naïve bays 

4. Logistic regression 

5. Support vector machines 

Topics 5: Unsupervised Machine Learning 

1. Clustering 

2. Principal components analysis 

3. Neural network overview 

4. Convolutional neural networks 

5. Autoencoders 

6. Recurrent neural networks 

Topics 6: Search with Artificial Intelligence (AI) 

1. Finding best route from origin to destination 

2. Agents, state, actions 

3. Transition model as a function 

4. State space by sequence of actions and directed graphs 

5. Goal tests and path costs 

Topics 7: Knowledge and Conclusions in AI 

1. Knowledge-based agents and sentences 

2. Propositional logics and symbols 

3. Logic connectives, Implication, Biconditional 

4. Knowledge based models 

5. Inference and knowledge engineering 

6. Modus ponen, elimination, double negation, De Morgan’s law, etc. 

Topics 8: AI for Uncertainty and Probability 

1. Possible worlds scenario and axioms in probability 

2. Unconditional and conditional probability 

3. Random variables and independence  

4. Baye’s rule and joint probability 

5. Probability rules: Negation, inclusion-exclusion, marginalization 

6. Bayesian networks, inference, sampling 

7. Markov’s models, assumptions, and chains 

Topics 9: Optimization of AI Algorithms 

1. Local search 

2. Hill climbing 

3. Simulated annealing 

4. Linear programming and constraint satisfaction 

5. Node and arc consistencies 

6. Backtracking search 

Topics 10: Neural Networks 

1. Activation functions 

2. Neural network structures 

3. Stochastic and mini-batch gradient descent 

4. Multilayer neural networks 

5. Back propagation and overfitting 

6. Tensor flow 

Topics 11: Computer Vision and Image Processing 

1. Computer vision and image convolution 

2. Convolutional neural networks 

3. Deep learning for computer vision 

4. Image classification and retrieval 

5. Object detection 

6. Semantic segmentation 

Topic 12: Project and Module 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