Lectures related to Loss functions for classification

Covers tensors, loss functions, autograd, and convolutional layers in deep learning.

Covers the fundamentals of deep learning, including data, architecture, and ethical considerations in model deployment.

Covers supervised learning, decision theory, risk minimization, and goal achievement.

Covers linear models for classification, logistic regression training, evaluation metrics, and decision boundaries.

Explores decision trees in machine learning, their flexibility, impurity criteria, and introduces boosting methods like Adaboost.

Explores the training and optimization of neural networks, addressing challenges like non-convex loss functions and local minima.

Covers the transition from a Monte Carlo approximation of the average to deriving batch and online update rules.