Theory of Machine Learning

GPTKB entity

Statements (60)
Predicate Object
gptkbp:instanceOf gptkb:academic
gptkbp:fieldOfStudy gptkb:machine_learning
gptkbp:focusesOn gptkb:information_theory
gptkb:probability_theory
gptkb:curse_of_dimensionality
gptkb:PAC_learning
gptkb:reinforcement_learning
gptkb:kernel_methods
gptkb:no_free_lunch_theorem
gptkb:empirical_risk_minimization
gptkb:VC_dimension
neural networks
online learning
optimization
gradient descent
statistical inference
supervised learning
active learning
bias-variance tradeoff
computational complexity
cross-validation
decision trees
ensemble methods
feature selection
overfitting
regularization
semi-supervised learning
support vector machines
underfitting
unsupervised learning
model selection
computational statistics
bagging
boosting
generalization
sample efficiency
convex optimization
probabilistic models
structural risk minimization
data complexity
learning curves
learning algorithms
model complexity
deep learning theory
sample distribution
loss functions
non-convex optimization
Bayesian learning theory
algorithmic foundations
algorithmic stability
convergence guarantees
learning bounds
risk minimization
sample complexity
https://www.w3.org/2000/01/rdf-schema#label Theory of Machine Learning
gptkbp:relatedTo gptkb:artificial_intelligence
learning theory
computational learning theory
gptkbp:bfsParent gptkb:Max_Planck_Institute_for_Intelligent_Systems
gptkbp:bfsLayer 3