Lectures related to Gather/scatter (vector addressing)

Support Vector Machines: Exercises Solutions

Covers solutions to SVM exercises, discussing optimality conditions, decision functions, and parameter impacts.

Support Vector Machines: Parameters, Solutions, and Boundaries

Explores SVM parameters, solutions, and decision boundaries, including the uniqueness of solutions and the impact of kernel width.

Support Vector Machines: Definition and Separation Hyperplane

Covers the history, linear separability, hyperplanes, and support vectors in Support Vector Machines.

Support Vector Machines: Hyperparameters and V-SVM

Explores SVM hyperparameters, V-SVM with variable p, and RVM.

Support Vector Machines: Linear Separability

Explores linear separability in support vector machines, focusing on hyperplane separation and margin optimization.

Support Vector Machines: Soft Margin

Explores Support Vector Machines with a focus on soft margin and multiclass classification using binary classifiers.

GPUs: Architecture and Programming

Explores GPUs' architecture, CUDA programming, image processing, and their significance in modern computing, emphasizing early start and correctness in GPU programming.

Support Vector Machines: Basics and Lagrange Duality

Covers the basics of Support Vector Machines and Lagrange Duality.

Support Vector Machine: Model Storage, Memory Usage, and Energy Consumption

Explores SVM model storage, memory usage, training time complexity, and energy consumption estimation.

Support Vector Machines: Dual Formulation for Hard Margin

Explores the dual formulation of Support Vector Machines for hard margin classification.

Linear SVM derivation

Covers the derivation of Linear Support Vector Machine (SVM) and the Karush-Kuhn-Tucker (KKT) conditions.

Vector Operations and Matrices

Covers basic vector operations in MATLAB and Octave.

Support Vector Machines: Theory and Applications

Explores Support Vector Machines theory, parameters, uniqueness, and applications in machine learning.

Support Vector Machines: SVM Basics

Covers the basics of Support Vector Machines, focusing on hard-margin and soft-margin formulations.

Support Vector Machines: Formulation and Complexity

Explores the formulation and complexity of Support Vector Machines, including primal and dual forms, geometric interpretation, and algorithmic implications.

GPUs: Architecture and Programming

Explores GPU architecture, multithreading, SIMD processors, and CUDA programming for parallel computing.

Natural Language Processing: Understanding Transformers and Tokenization

Provides an overview of Natural Language Processing, focusing on transformers, tokenization, and self-attention mechanisms for effective language analysis and synthesis.

Support Vector Machines: Maximizing Margin

Explores Support Vector Machines, maximizing margin for robust classification and the transition to soft SVM for non-linearly separable data.

SVM Hyperparameters

Delves into SVM hyperparameters, showcasing the impact of C and kernel width on classification results.

Support Vector Machine: Primal Formulation with Hard Margin

Covers the Support Vector Machine with a hard margin formulation and the importance of maximizing the margin between classes.