Lectures related to Multi-class Problems: One-hot Coding

Discusses statistical view of neural networks, classification tasks, and cross-entropy loss functions.

Explains the learning process in multi-layer neural networks, including back-propagation, activation functions, weights update, and error backpropagation.

Variational Formulation: Information Measures

Explores variational formulation for measuring information content and divergence between probability distributions.

Information Measures: Entropy and Information Theory

Explains how entropy measures uncertainty in a system based on possible outcomes.

Interpreting Output as Probability

Delves into interpreting neural network output as probabilities based on the cross-entropy error function.

Interpretation of Entropy

Explores the concept of entropy expressed in bits and its relation to probability distributions, focusing on information gain and loss in various scenarios.

Probability Distribution and Entropy

Explains probability distribution, entropy, and Gibbs free entropy, along with the Weiss model.

Neural Networks: Multilayer Perceptrons

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

Entropy and KL Divergence

Explores entropy, KL divergence, and maximum entropy principle in probability models for data science.

Neural Networks: Training and Activation

Explores neural networks, activation functions, backpropagation, and PyTorch implementation.

Sigmoidal Units: Natural Output Functions

Delves into using sigmoidal units as natural output functions in deep learning, focusing on statistical interpretation and optimal derivation.

Random Walks and Moran Model in Population Genetics

Explores random walks, Moran model, bacterial chemotaxis, entropy, information theory, and coevolving sites in proteins.

Building a Decision Tree

Covers building decision trees to classify mushrooms as poisonous or not.

Model Selection Criteria: AIC, BIC, Cp

Explores model selection criteria like AIC, BIC, and Cp in statistics for data science.

Information Measures: Estimation & Detection

Covers information measures, entropy, mutual information, and data processing inequality in signal representation.

Multilayer Perceptron: Training and Optimization

Explores the multilayer perceptron model, training, optimization, data preprocessing, activation functions, backpropagation, and regularization.

Untitled

Entropy Bounds: Conditional Entropy Theorems

Explores entropy bounds, conditional entropy theorems, and the chain rule for entropies, illustrating their application through examples.

Deep Learning: Multilayer Perceptron and Training Log in to Mediaspace to watch this video

Covers deep learning fundamentals, focusing on multilayer perceptrons and their training processes.

Linear Models for Classification: Multi-Class Extensions Log in to Mediaspace to watch this video

Covers linear models for multi-class classification, focusing on logistic regression and evaluation metrics.