Gradient Descent: MNIST Dataset and Logistic Loss

Related lectures (30)

Page 3 of 3

Discusses the gradient method for optimization, focusing on its application in machine learning and the conditions for convergence.

Covers the Perceptron model, SGD, and Fisher's Linear Discriminant in binary classification.

Introduces decision trees and k-nearest neighbors for classification tasks, exploring metrics like accuracy and AUC.

Explores document analysis, topic modeling, and generative models for data generation in machine learning.

Introduces fundamental machine learning concepts, covering regression, classification, dimensionality reduction, and deep generative models.

Explores gradient descent, loss functions, and optimization techniques in neural network training.

Covers data representations, Bag of Words, histograms, data pre-processing, and neural networks.

Explores linear models for classification, including logistic regression, decision boundaries, and support vector machines.

Covers stochastic gradient descent, linear regression, regularization, supervised learning, and the iterative nature of gradient descent.

Introduces deep learning, from logistic regression to neural networks, emphasizing the need for handling non-linearly separable data.