Lecture
Learning Sparse Features: Overfitting in Neural Networks
Related lectures (77)
Geometric ConstraintsMOOC: Newton's Mechanics
Explores how to handle mechanical problems with geometric constraints and associated forces.
Deep Learning: Dimensionality and Data Representation
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.
Introduction to sensory learningMOOC: Neuro Robotics
Explores sensor representations and learning rules to understand how complex sensor representations emerge.
Graph Neural Network Architectures: A Comparative Study
Explores the choice of graph neural network architectures, evaluating model complexity and performance based on data statistics.
Regularization by Early Stopping
Explores regularization by early stopping in deep neural networks to control flexibility and avoid overfitting.
Electric Field Calculation: Charged Half-Sphere
Explores the calculation of electric fields from a charged half-sphere, emphasizing symmetry considerations and efficient problem-solving techniques.
Advanced Machine Learning: Feature Selection
Explores machine learning algorithms, feature selection techniques like FAST and BRIEF descriptors, and the limitations of deep learning.
RANSAC: Robust Outlier Detection and Applications
Explores the RANSAC algorithm for outlier detection and its diverse applications in Machine Learning.
Intersection between Sphere and Cone
Explores the intersection between a sphere and a cone using spherical and cylindrical coordinates.
Self-Supervised Learning: State of the Art
Explores self-supervised learning, transfer learning, SSL prediction tasks, feature learning, image rotations, contrastive learning, and vision learners.