Graduate School of health and Medical Sciences

Introduction to Machine Learning and Deep Learning
Provider: Faculty of Health and Medical Sciences

Activity no.: 3953-25-00-00	There are 14 available seats
	Enrollment deadline: 04/04/2025

Date and time	05.05.2025, at: 08:00 - 07.05.2025, at: 15:00
Regular seats	30
Course fee	2,040.00 kr.
Lecturers	Thomas Gerds
ECTS credits	2.10

Contact person	Susanne Kragskov Laupstad E-mail address: skl@sund.ku.dk

Enrolment Handling/Course Organiser	PhD administration E-mail address: phdkursus@sund.ku.dk

Aim and content This is a generic course. This means that the course is reserved for PhD students at the Graduate School of Health and Medical Sciences at UCPH. Anyone can apply for the course, but if you are not a PhD student at the Graduate School, you will be placed on the waiting list until enrollment deadline. After the enrollment deadline, available seats will be allocated to the waiting list. The course is free of charge for PhD students at Danish universities (except Copenhagen Business School), and for PhD students at NorDoc member faculties. All other participants must pay the course fee. Background Machine Learning (ML) and Deep Learning (DL) are rapidly evolving fields that have revolutionized numerous domains, including healthcare, finance, image processing, and natural language processing. In biomedical science, ML and DL have enabled breakthroughs in disease prediction, imaging analysis, and precision medicine. This course provides an introduction to the fundamental concepts and methods of ML and DL, with an emphasis on their practical applications. Starting with basic supervised and unsupervised learning techniques, the course transitions to advanced neural network architectures and optimization techniques used in DL. The goal is to equip participants with a foundational understanding of these powerful tools and hands-on experience applying them effectively in practice. Key topics include the essential building blocks of ML, such as classification and regression, hyperparameter tuning, and performance evaluation metrics like accuracy, recall, and precision. The course will also cover the unique aspects of DL, such as backpropagation, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers, which form the backbone of modern DL applications. Through demonstrations, practical exercises, and coding in R and Python, participants will gain insights into the differences between ML/DL and traditional statistical methods and learn to use these tools to solve real-world problems. Understand core concepts of ML, such as: 1.Supervised vs. unsupervised learning. 2.Classification and regression tasks. 3.Bias-variance tradeoff and model evaluation (e.g., F1-score, recall, and precision). 4.Cross-validation techniques for robust model performance evaluation. Explore applications of unsupervised learning, including: 1.Clustering methods like K-means and image segmentation. 2.Dimensionality reduction techniques such as PCA and SVD. 3.Autoencoder architectures for non-linear dimensionality reduction. Gain familiarity with fundamental DL topics, including: 1.Fully connected architectures and activation functions. 2.The backpropagation algorithm and weight initialization techniques. 3.Regularization methods, such as dropout and batch normalization, to mitigate overfitting. 4.Architectures like CNNs for image data and RNNs/LSTMs for sequential data. 5.Transformers for cutting-edge applications in natural language processing and beyond. Develop hands-on skills using R and Python for ML/DL tasks: 1.Building, training, and evaluating ML models. 2.Implementing neural network architectures using popular frameworks like TensorFlow or PyTorch. 3.Diagnosing overfitting and optimizing hyperparameters for robust model performance. Prerequisites The course is designed for participants with basic knowledge of programming (preferably in R or Python) and introductory statistics, including concepts like mean, variance, and linear regression. While prior experience with machine learning is not required, familiarity with concepts like Maximum Likelihood Estimation or general optimization is helpful. Participants Ph.D. students in medicine, epidemiology, bioscience or biostatistics, and other scientists. Max. 30 participants. Language English Form 3 days consecutive days Course director Professor Thomas Gerds Teachers Professor Benoit Liquet. University of Pau et Pays de l'Adour, France Course secretary Susanne Kragskov Laupstad, Department of Public Health, Section of Biostatistics, University of Copenhagen, e-mail: skl@sund.ku.dk Dates 5-7 May 2025 from 8-15. Registration Please register before 4 April 2025 Admission to PhD students from Danish universities will be allocated on a first-come, first-served basis and according to the rules in force. Applications from other participants will be considered after last day of enrollment. Note: All applicants are asked to submit invoice details in case of no-show, late cancellation or obligation to pay the course fee (typically non-PhD students). If you are a PhD student, your participation in the course must be in agreement with your principal supervisor.

Click the search button to search Courses.

See which courses you can attend and when

Jan	Feb	Mar	Apr
May	Jun	Jul	Aug
Sep	Oct	Nov	Dec

New courses
Courses are published regularly. High demand courses are announced in spring and autumn.

Learn which courses are announced on fixed dates