Concept

Hyperparameter

Related lectures (17)

Exponential Family: Maximum Entropy Distribution

Covers exponential families, maximum entropy, and Moxwell-Boltzmann distribution properties.

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

SVM Hyperparameters

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

Quantifying Performance: Misclassification and F-Measure

Covers quantifying performance through true positives, false negatives, and false positives in machine learning.

Bayesian Inference: Precision in Gaussian Model

Explores Bayesian inference for precision in the Gaussian model with known mean, using a Gamma prior and discussing subjective vs objective priors.

Bayesian Estimation: Overview and Examples

Introduces Bayesian estimation, covering classical versus Bayesian inference, conjugate priors, MCMC methods, and practical examples like temperature estimation and choice modeling.

Deep Learning Techniques: Recurring Networks and LSTM Models

Discusses the implementation and optimization of recurring networks using LSTM models in deep learning.

Model Complexity and Overfitting in Machine Learning

Covers model complexity, overfitting, and strategies to select appropriate machine learning models.

Machine Learning Basics

Introduces machine learning basics, including data collection, model evaluation, and feature normalization.

Support Vector Regression: Nu-SVR and RVR

Explores advanced topics in machine learning, focusing on SVR extensions and hyperparameter optimization, including Nu-SVR and RVR.

Using cross-validation: Building a final predictor

Covers the interpretation of cross-validation risk estimates and building a final predictor from cross-validation results.

Machine Learning Phases

Explains the importance of training, validation, and test sets in machine learning phases.

Backpropagation and Neural Networks

Covers the backpropagation algorithm for training neural networks and the representation of functions in multilayer networks.

Simple validation, cross-validation, leave-one-out

Introduces techniques for obtaining unbiased risk estimates of learned predictors and their application for hyperparameter tuning.

Unsupervised Machine Learning: Clustering Basics

Introduces unsupervised machine learning clustering techniques like K-means, Gaussian Mixture Models, and DBSCAN, explaining their algorithms and applications.

General-Purpose Distributed Execution System

Explores the design of a general-purpose distributed execution system, covering challenges, specialized frameworks, decentralized control logic, and high-performance shuffle.

Kernel Methods in Machine Learning: Kernel Regression and SVM

Discusses kernel methods in machine learning, focusing on kernel regression and support vector machines, including their formulations and applications.