Lecture

Linear Models for Classification: Recap and Binary Classification

Related lectures (32)

Explores model checking and residuals in regression analysis, emphasizing the importance of diagnostics for ensuring model validity.

Linear Models & k-NN

Covers linear models, logistic regression, decision boundaries, k-NN, and practical applications in authorship attribution and image data analysis.

Neural Networks: Multilayer Perceptrons

Covers Multilayer Perceptrons, artificial neurons, activation functions, matrix notation, flexibility, regularization, regression, and classification tasks.

Kernel Regression: K-nearest Neighbors

Covers the concept of kernel regression and K-nearest neighbors for making data linearly separable.

Linear Models for Classification

Explores linear models for classification, including parametric models, regression, and logistic regression, along with model evaluation metrics and maximum margin classifiers.

Regression and Classification

Explores regression, classification, linear models, decision trees, and random forests in data analysis.

Generalized Linear Models

Covers probability, random variables, expectation, GLMs, hypothesis testing, and Bayesian statistics with practical examples.

Regression Analysis: Linear Predictors

Delves into regression analysis, emphasizing linear predictors' role in approximating outcomes and discussing generalized linear models and causal inference techniques.

Linear Models for Classification: Logistic Regression and SVM

Covers linear models for classification, focusing on logistic regression and support vector machines.

Binary Classification by Regression: Decision Functions and Cost Functions

Explores binary classification by regression, decision functions, and various cost functions.

Linear Models: Recap and Logistic Regression

Covers linear models, binary classification, logistic regression, and model evaluation metrics.

Estimation, Shrinkage and Penalization

Covers estimation, shrinkage, and penalization in statistics for data science, emphasizing the importance of balancing bias and variance in model estimation.