Machine learning and deep learning fundamentals

Machine learning and deep learning are transforming research by enabling data-driven discoveries and predictive modeling. For many researchers, these techniques can unlock new insights from complex datasets, but getting started can feel overwhelming. This two-day workshop is designed for researchers with little or no prior experience in machine learning who want to apply these methods in their own work.

Learning outcomes

Explain the fundamental concepts of machine learning and deep learning
Apply data preprocessing techniques such as handling missing values, scaling features, and splitting datasets
Implement regression and classification models with scikit-learn and evaluate their performance using appropriate metrics
Construct simple neural networks and convolutional neural networks with PyTorch framework
Identify issues with model behavior, like overfitting, and adopt solutions such as regularization or dropout
Interpret the results of machine learning and deep learning models to make informed decisions for research applications

Approach

Through a mix of clear explanations and hands-on exercises in Jupyter notebooks, you will learn how to process data, build regression and classification models, and train neural networks and convolutional neural networks.

Required skills

No prior machine learning experience
Familiarity with Python will be required (recommended course: Programming in Python: master your first project)

Machine learning and deep learning fundamentals

Upcoming events