Concept
Hyperparameter optimization
Related lectures (64)
Multilayer Neural Networks: Deep Learning
Covers the fundamentals of multilayer neural networks and deep learning.
Using cross-validation: Building a final predictor
Covers the interpretation of cross-validation risk estimates and building a final predictor from cross-validation results.
Deep Learning for Autonomous Vehicles: Learning
Explores learning in deep learning for autonomous vehicles, covering predictive models, RNN, ImageNet, and transfer learning.
Adaptive Optimization Methods: Theory and Applications
Explores adaptive optimization methods that adapt locally and converge without knowing the smoothness constant.
Deep Generative Models in Drug Discovery
Explores the application of deep generative models in drug discovery, focusing on designing small molecules and optimizing molecular structures.
Decision Trees: Classification
Explores decision trees for classification, entropy, information gain, one-hot encoding, hyperparameter optimization, and random forests.
Adaptive Gradient Methods: Theory and Applications
Explores adaptive gradient methods, their properties, convergence, and comparison with traditional optimization algorithms.
Building Neural Networks: Assembly Strategies
Focuses on assembling neural network building blocks and dealing with data sparseness using various strategies and assumptions.
Generalized Linear Regression
Explores generalized linear regression, logistic regression, and multiclass classification in machine learning.
Gradient Descent: Early Stopping and Stochastic Gradient Descent
Explains gradient descent with early stopping and stochastic gradient descent to optimize model training and prevent overfitting.