One of the most important applications of AI in engineering is classification and regression using machine learning. After taking this course, students will have a clear understanding of essential concepts in machine learning, and be able to fluently use popular machine learning techniques in science and engineering problems via MATLAB. Among the many machine learning methods, only those with the best performance and are widely used in science and engineering are carefully selected and taught. To avoid students getting lost in details, in contrast to teaching machine learning methods one by one, the first two lectures display the global picture of machine learning, making students clearly understand essential concepts and the working principle of machine learning. Data preparation is then introduced, followed by two popular machine learning methods, support vector machines and artificial neural networks. Practical cases in science and engineering are provided, making sure students have the ability to apply what they have learned in real practice. In addition, MATLAB classification and regression apps, which allow easy access to many machine learning methods, are introduced. In partnership with MathWorks, enrolled students have access to MATLAB for the duration of the course.
JJ
The support from teaching staff is timely and helpful.
C
Finished feeling confident to put “ML skills” on my CV.
MM
The pacing is perfect: conceptual overview first, then data prep, then deep dives—no cognitive overload at any point.
HH
Real-world examples help connect theory to application.
EE
Perfect balance of theory, coding, and real-world examples.
II
The pace is suitable for students with limited coding background.
BB
Labs give instant results—achievement unlocked every time.
GG
The course improves both understanding and practical skills.
RR
Best educational tech experience I’ve had in grad school.
EE
The selected algorithms are highly relevant to engineering problems.
WW
The data-preparation module alone saved me weeks of trial-and-error; I finally understand why "garbage in, garbage out" is 80 % of the battle.
CC
Quizzes are woven into the labs, so I got instant feedback on whether my model was actually converging or just looking pretty.
Showing: 20 of 34
This course delivers a perfect balance between foundational machine learning theory and hands-on implementation using Python, empowering engineers to tackle real-world data challenges confidently.
From linear regression to deep neural networks, the course structure ensures smooth progression for learners at all levels—highly recommended for both beginners and experienced professionals.
This course’s emphasis on practical machine learning pipelines—from data preprocessing to model deployment—has made me a more efficient and confident engineer in AI-driven projects.
The instructor’s deep understanding of supervised and unsupervised learning techniques transformed abstract concepts like SVMs and clustering into practical tools I can apply daily.
The instructor’s emphasis on reproducibility and version control in ML workflows has transformed how I manage collaborative projects in research and industry settings.
Interactive Jupyter Notebook exercises with real-world datasets made complex topics like reinforcement learning and computer vision feel approachable and engaging.
This course is a game-changer for professionals seeking to transition into data science—equipping you with both technical depth and industry-ready applications.
The course’s focus on interpretability tools has equipped me to explain ML models to non-technical stakeholders—a critical skill in industrial AI adoption.
This course is a must for professionals seeking to leverage machine learning for innovation—in fields ranging from autonomous systems to climate modeling.
By the end I could reproduce a published paper's result in half a day; the course genuinely bridged the gap between theory and publishable practice.
The data-preparation module alone saved me weeks of trial-and-error; I finally understand why "garbage in, garbage out" is 80 % of the battle.
The Kaggle-based projects and model deployment workshops gave me tangible skills to build end-to-end ML pipelines in production environments.
Quizzes are woven into the labs, so I got instant feedback on whether my model was actually converging or just looking pretty.
The pacing is perfect: conceptual overview first, then data prep, then deep dives—no cognitive overload at any point.
Finally, a class that teaches only the ML tools you’ll actually use in research.
One sentence from the prof saved me three months of literature digging.
The selected algorithms are highly relevant to engineering problems.
The pace is suitable for students with limited coding background.
Data prep section alone rescued countless hours of my lab life.
The course improves both understanding and practical skills.