Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers the curse of dimensionality, which implies that in high dimensions, data points become increasingly isolated, requiring more training data. Methods for variable selection, such as filtering based on correlation or mutual information, are discussed. The coefficient of determination is introduced as a measure of how well predicted values correlate with actual values. Limitations of filtering methods are highlighted, using the example of explaining the output of an exclusive OR (XOR) operation. Overall, the lecture emphasizes the challenges and strategies for reducing dimensionality in machine learning.
This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.
Watch on Mediaspace