Delves into deep learning's dimensionality, data representation, and performance in classifying large-dimensional data, exploring the curse of dimensionality and the neural tangent kernel.
Covers feature extraction, clustering, and classification methods for high-dimensional datasets and behavioral analysis using PCA, t-SNE, k-means, GMM, and various classification algorithms.
Covers the basics of image processing for Earth observation, including course objectives, administration details, interdisciplinary aspects, and key image processing concepts.
Introduces Lasso regularization and its application to the MNIST dataset, emphasizing feature selection and practical exercises on gradient descent implementation.