À propos de ce cours : Probabilistic graphical models (PGMs) are a rich framework for encoding probability distributions over complex domains: joint (multivariate) distributions over large numbers of random variables that interact with each other. These representations sit at the intersection of statistics and computer science, relying on concepts from probability theory, graph algorithms, machine learning, and more. They are the basis for the state-of-the-art methods in a wide variety of applications, such as medical diagnosis, image understanding, speech recognition, natural language processing, and many, many more. They are also a foundational tool in formulating many machine learning problems. This course is the third in a sequence of three. Following the first course, which focused on representation, and the second, which focused on inference, this course addresses the question of learning: how a PGM can be learned from a data set of examples. The course discusses the key problems of parameter estimation in both directed and undirected models, as well as the structure learning task for directed models. The (highly recommended) honors track contains two hands-on programming assignments, in which key routines of two commonly used learning algorithms are implemented and applied to a real-world problem.
Créé par : Université de Stanford
Enseigné par : Daphne Koller, Professor
School of Engineering
| Informations de base | Cours 3 de 3 dans Probabilistic Graphical Models Specialization |
| Niveau | Advanced |
| Langue | English |
| Comment réussir | Réussissez tous les devoirs notés pour terminer le cours. |
| Notes des utilisateurs |
Programme de cours
SEMAINE 1
Learning: Overview
This module presents some of the learning tasks for probabilistic graphical models that we will tackle in this course.
1 vidéo
Review of Machine Learning Concepts from Prof. Andrew Ng's Machine Learning Class (Optional)
This module contains some basic concepts from the general framework of machine learning, taken from Professor Andrew Ng's Stanford class offered on Coursera. Many of these concepts are highly relevant to the problems we'll tackle in this course.
6 vidéos
- Vidéo: Regularization: Cost Function
- Vidéo: Evaluating a Hypothesis
- Vidéo: Model Selection and Train Validation Test Sets
- Vidéo: Diagnosing Bias vs Variance
- Vidéo: Regularization and Bias Variance
Parameter Estimation in Bayesian Networks
This module discusses the simples and most basic of the learning problems in probabilistic graphical models: that of parameter estimation in a Bayesian network. We discuss maximum likelihood estimation, and the issues with it. We then discuss Bayesian estimation and how it can ameliorate these problems.
5 vidéos
- Vidéo: Maximum Likelihood Estimation for Bayesian Networks
- Vidéo: Bayesian Estimation
- Vidéo: Bayesian Prediction
- Vidéo: Bayesian Estimation for Bayesian Networks
Noté: Learning in Parametric Models
Noté: Bayesian Priors for BNs
SEMAINE 2
Learning Undirected Models
In this module, we discuss the parameter estimation problem for Markov networks - undirected graphical models. This task is considerably more complex, both conceptually and computationally, than parameter estimation for Bayesian networks, due to the issues presented by the global partition function.
3 vidéos
- Vidéo: Maximum Likelihood for Conditional Random Fields
- Vidéo: MAP Estimation for MRFs and CRFs
Noté: Parameter Estimation in MNs
Noté: CRF Learning for OCR
SEMAINE 3
Learning BN Structure
This module discusses the problem of learning the structure of Bayesian networks. We first discuss how this problem can be formulated as an optimization problem over a space of graph structures, and what are good ways to score different structures so as to trade off fit to data and model complexity. We then talk about how the optimization problem can be solved: exactly in a few cases, approximately in most others.
7 vidéos
- Vidéo: Likelihood Scores
- Vidéo: BIC and Asymptotic Consistency
- Vidéo: Bayesian Scores
- Vidéo: Learning Tree Structured Networks
- Vidéo: Learning General Graphs: Heuristic Search
- Vidéo: Learning General Graphs: Search and Decomposability
Noté: Structure Scores
Noté: Tree Learning and Hill Climbing
Noté: Learning Tree-structured Networks
SEMAINE 4
Learning BNs with Incomplete Data
In this module, we discuss the problem of learning models in cases where some of the variables in some of the data cases are not fully observed. We discuss why this situation is considerably more complex than the fully observable case. We then present the Expectation Maximization (EM) algorithm, which is used in a wide variety of problems.
5 vidéos
- Vidéo: Expectation Maximization - Intro
- Vidéo: Analysis of EM Algorithm
- Vidéo: EM in Practice
- Vidéo: Latent Variables
Noté: Learning with Incomplete Data
Noté: Expectation Maximization
Noté: Learning with Incomplete Data
SEMAINE 5
Learning Summary and Final
This module summarizes some of the issues that arise when learning probabilistic graphical models from data. It also contains the course final.
1 vidéo
Noté: Learning: Final Exam
PGM Wrapup
This module contains an overview of PGM methods as a whole, discussing some of the real-world tradeoffs when using this framework in practice. It refers to topics from all three of the PGM courses.
1 vidéo
FAQ
Comment cela fonctionne
Coursework
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Help from Your Peers
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Certificates
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
Créateurs
Université de Stanford
The Leland Stanford Junior University, commonly referred to as Stanford University or Stanford, is an American private research university located in Stanford, California on an 8,180-acre (3,310 ha) campus near Palo Alto, California, United States.
Tarification
| Acheter le cours | |
|---|---|
| Accéder au contenu du cours | Disponible |
| Accéder au contenu noté | Disponible |
| Recevoir une Note Finale | Disponible |
| Obtenir un Certificat de Cours partageable | Disponible |
Notation et examens
very good course for PGM learning and concept for machine learning programming. Just some description for quiz of final exam is somehow unclear, which lead to a little bit confusing.
Great course! It is pretty difficult - be prepared to study. Leave plenty of time before the final exam.
Just completed the 3 course specialization. If you're interested (and already have some background) in Machine Learning, this specialization is totally worth it. However, if you have trouble solving any of the quizzes or assignments, do not expect to have any kind of support from the TAs. They simply do not respond to any post in the forum, even if it is related with any bug in the programming assignments source code.
Coursera propose un accès universel à la meilleure formation au monde,
en partenariat avec des universités et des organisations du plus haut niveau, pour proposer des cours en ligne.
© 2018 Coursera Inc. Tous droits réservés.
Yeah! I managed to finish PGM. I feel ready to explore further. PGM 3 is really helpful. Although many details are not fully discussed, some important intuitions are well illustrated, like EM algorithm and its modification in case of incomplete data. Also, the way the teacher teach set an good example for me to learn to demonstrate complicated things in an easy and vivid way. Thank you so much!