ConceptAI & ML
Maximum likelihood estimation
Estimating parameters by maximizing the log-likelihood function of the observed data under a parametric model.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Probability4Logarithm3Optimization2Probability density function2Empirical frequency1Factor analysis model1Likelihood1Likelihood function1
Opens up
Concepts that name this one as a prerequisite.
Concentrated log likelihood2EM algorithm2Limited information maximum likelihood2Logistic regression2Model selection criteria2Bias of maximum likelihood estimator for variance1Continuous normalizing flow1Contrastive divergence1Covariance estimation1Cross-entropy error1Cross-entropy loss1Cross-entropy method1
Lecturers
6Each in their own terms, from the easiest level.
Pieter Abbeel
A framework where you maximize the likelihood of the data to find good parameter vectors.Jason Wei & Hyung Won Chung
A training paradigm where a model treats a single target as the only correct answer while all other possibilities are treated as incorrect.Peter Kempthorne
A method of estimating the parameters of a probability distribution by maximizing a likelihood function, assuming normal distributions for the model's random variables.Ben Olken
An approach where you specify the full likelihood function from the data and the data-generating process to find the parameters that maximize the likelihood of observing that data.Peter Kempthorne, Jake Xia & Vasily Strela
The method of finding parameter values that maximize the likelihood function, making the observed data most likely in terms of its probability density function.
Lectures that assume it
21The first 12 are shown.
- Surrogate Modeling and Bayesian Optimization
- The Linear Model II
- Convex Optimization II: Truncated Newton Method and L1-Norm Methods
- Exploration of advanced topics in deep reinforcement learning
- Radial Basis Functions
- Surrogate Modeling and Bayesian Optimization (Part 2)
- Sequential Convex Programming
- Time Series Analysis III
- Generative Models: Representation Learning Meets Generative Modeling
- Reinforcement Learning from Human Feedback: Algorithms & Applications
- Loss Functions and Optimization
- An Observation on Generalization and Unsupervised Compression
Connections
38The lectures that define it or assume it, and the concepts next to it.
Concepts9
Show 3 moreShow fewer
Lectures29
- Statistical Estimation
- Machine Learning: Optimization and Neural Networks
- Intuitions on Language Models and the History of Transformer Architectures
- Machine Learning: Naive Bayes
- Machine Learning: Perceptrons and Logistic Regression
- Factor Modeling
Show 23 moreShow fewer
- Public Finance (Part 2)
- Time Series Analysis I
- Surrogate Modeling and Bayesian Optimization
- The Linear Model II
- Convex Optimization II: Truncated Newton Method and L1-Norm Methods
- Exploration of advanced topics in deep reinforcement learning
- Radial Basis Functions
- Surrogate Modeling and Bayesian Optimization (Part 2)
- Sequential Convex Programming
- Time Series Analysis III
- Generative Models: Representation Learning Meets Generative Modeling
- Reinforcement Learning from Human Feedback: Algorithms & Applications
- Loss Functions and Optimization
- An Observation on Generalization and Unsupervised Compression
- Probably Approximately Precision and Recall Learning
- Reflecting on Neural ODEs at NeurIPS 2019
- Policy Gradient Methods
- Integrating Learning and Planning
- Time Series Analysis II
- Generative Models: Basics
- Volatility Modeling
- Exploration of fundamental concepts in deep reinforcement learning
- Exploration of advanced topics in deep reinforcement learning