Course content

• What is machine learning:
  • How does machine learning differ from traditional programming? Correlation Vs Causation
  • Types of learning: Supervised, Unsupervised, Semi-Supervised and Reinforcement Learning
  • Difference between ML in research and in Production.
• Data Visualization using matplotlib and seaborn libraries
• Data preparation
  • How do I represent my data so that an algorithm can learn from it using the Pandas Library function?
  • Diversity and bias in data: How to identify that the prediction task is trained on representative data, Bias identification.
  • Feature engineering: Feature Selection and Feature Transformation.
• Machine learning Python libraries and practice
  • Machine learning libraries: Numpy, Pandas, Scikit-learn, Scipy, Tensorflow and Pytorch (for deep learning)
• Machine learning algorithms for Supervised and Unsupervised Learning
  • Linear and Logistic Regression, Decision trees, Support Vector Machines, K-means, K Nearest Neighbours, Dimensionality Reduction, Ensemble learning etc.
• Evaluation of results
  • Evaluation metrics. how to quantify "how bad" the prediction was? How do I increase the model's accuracy? Bias Variance tradeoff.
• AI ethics, responsibility, consequences
  • Case studies on model biases in the real world.
• Machine learning application practice in specialized domains, including:
  • Energy
  • Maritime
  • Medical

Learning outcome

Upon completion of the course, students will be expected to:

1) Learn basic concepts of machine learning such as supervised, unsupervised learning, regression, classification tasks, data preprocessing, data visualization, different models for supervised and unsupervised learning, regression, and classification tasks, and choosing the right model and evaluating the model.

2) Be able to design and implement various machine learning algorithms in a range of real-world applications. Have a good understanding of the fundamental issues and challenges of machine learning data, bias, model selection, model complexity, etc.

3) Understand key elements of how to use machine learning in applications that require images, videos, text, time series, etc. Have an understanding of the strengths and weaknesses of many popular machine learning approaches.

4) Conduct research and apply tools and technologies in different areas such as recommendation systems, image segmentation, sentiment analysis, text understanding and text summarization, object detection, and tracking, etc. Be ready for taking advanced course on Deep Learning and Generative AI models.

Learning methods and activities

Lectures for 4 hours along with exercises covering the entire course. Other supporting material (video, text, etc.) may be used. Mandatory assignments: 3 to be eligible for the oral exam

Compulsory assignments

• Assignments

Recommended previous knowledge

The course does not presume or require any prior knowledge in machine learning. However, to understand the concepts presented and complete the exercise, we recommend that students meet the following prerequisites:

• Mastery of intro-level algebra: you should be comfortable with variables and coefficients, linear equations, graphs of functions. Being familiar with more advanced math concepts such derivatives is very helpful but not required.
• Proficiency in programming basics: it is highly recommended that you feel comfortable reading and writing Python code before starting this course. The programming exercise in the machine learning course uses Keras and pandas libraries.
• It is expected that Matlab programmers will find no problem to switch to Python.

Course materials

Reading list:

A. Geron. Hands-On Machine Learning with SciKit-Learn & TensorFlow: concepts, tools, & techniques to build intelligent systems. 2017, O'Reilly.

Materials, handouts, quizzes from various sources will be provided throughout the semester.

Credit reductions