Semester:

7

Course Code:

CE5770

Course Name:

Artificial Intelligence and Machine Learning

Credit Value:

2 (Notional hours:100)

Prerequisites:

None

Core/Optional

Optional

Hourly Breakdown

Lecture hrs.

Tutorial hrs.

Practical hrs.

Independent Learning & Assessment hrs.

20

-

20

60

Course Aim: To introduce the fundamentals, models and techniques commonly used in artificial intelligence applications, particularly in machine learning.

Intended Learning Outcomes:

On successful completion of the course, the students should be able to;

➢    explain the advantages of and limitations in choosing Machine Learning methods for different applications.

➢    design experiments using Machine Learning methods with the emphasis on evaluation.

➢    implement algorithms for selected methods.

Course Content:

➢    Introduction to Machine Learning: Applications of machine learning

➢    Machine Learning Algorithms: Supervised Learning (Classification, Regression and Ranking), Unsupervised Learning (Clustering and Dimensionality Reduction)

➢    Regression with one input variables: Cost function, Gradient descent algorithm: Minimizing cost function

➢    Regression with multiple input variables: Methods for improving training and performance of models, such as vectorization, feature scaling, feature engineering and polynomial regression

➢    Logistic Regression: Classification algorithm: Hypothesis representation, Decision boundary

➢    Overfitting : Regularization

➢    Clustering: Introduction to Clustering, The k-means Algorithm, Mean Shift Algorithm

➢    Neural Networks: Nonlinear hypothesis, Model representation, cost function, forward and backward propagation algorithms, Case studies related to Civil Engineering

Teaching /Learning Methods:

Classroom lectures, tutorial discussions, software application, group exercises

Assessment Strategy:

Continuous Assessment

50%

Final Assessment

50%

Details:

Assignment/Quizzes    20%

Mini Project       30%

Theory (%)

50

Practical (%)

-

Other (%)

-

Recommended Reading:

➢    Aurélien Géron, (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd edition, O'Reilly Media, Inc.

➢    Marc Peter Deisenroth. (2014). Mathematics for Machine Learning, 5th edition, Cambridge University Press.