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.
Ce cours fait partie de la Spécialisation Modèles graphiques probabilistes
Offert par
Spécialisation Modèles graphiques probabilistes Université de StanfordÀ propos de ce cours
14,066 consultations récentes
Résultats de carrière des étudiants
43%
ont commencé une nouvelle carrière après avoir terminé ce cours
29%
ont bénéficié d'un avantage concret dans leur carrières grâce à ce cours
17%
a obtenu une augmentation de salaire ou une promotion
Certificat partageable
Obtenez un Certificat lorsque vous terminez
100 % en ligne
Commencez dès maintenant et apprenez aux horaires qui vous conviennent.
Cours 3 sur 3 dans le
Dates limites flexibles
Réinitialisez les dates limites selon votre disponibilité.
Niveau avancé
Approx. 66 heures pour terminer
Anglais
Sous-titres : Français, Portugais (brésilien), Russe, Anglais, Espagnol
Compétences que vous acquerrez
AlgorithmsExpectation–Maximization (EM) AlgorithmGraphical ModelMarkov Random Field
Résultats de carrière des étudiants
43%
ont commencé une nouvelle carrière après avoir terminé ce cours
29%
ont bénéficié d'un avantage concret dans leur carrières grâce à ce cours
17%
a obtenu une augmentation de salaire ou une promotion
Certificat partageable
Obtenez un Certificat lorsque vous terminez
100 % en ligne
Commencez dès maintenant et apprenez aux horaires qui vous conviennent.
Cours 3 sur 3 dans le
Dates limites flexibles
Réinitialisez les dates limites selon votre disponibilité.
Niveau avancé
Approx. 66 heures pour terminer
Anglais
Sous-titres : Français, Portugais (brésilien), Russe, Anglais, Espagnol
Offert par
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.
Programme du cours : ce que vous apprendrez dans ce cours
16 minutes pour terminer
Learning: Overview
This module presents some of the learning tasks for probabilistic graphical models that we will tackle in this course.
16 minutes pour terminer
1 vidéo (Total 16 min)
1 vidéo
Learning: Overview15 min
1 heure pour terminer
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.
1 heure pour terminer
6 vidéos (Total 59 min)
6 vidéos
Regularization: Cost Function 10 min
Evaluating a Hypothesis 7 min
Model Selection and Train Validation Test Sets 12 min
Diagnosing Bias vs Variance 7 min
Regularization and Bias Variance11 min
2 heures pour terminer
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.
2 heures pour terminer
5 vidéos (Total 77 min)
5 vidéos
Maximum Likelihood Estimation for Bayesian Networks15 min
Bayesian Estimation15 min
Bayesian Prediction13 min
Bayesian Estimation for Bayesian Networks17 min
2 exercices pour s'entraîner
Learning in Parametric Models30 min
Bayesian Priors for BNs30 min
21 heures pour terminer
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.
21 heures pour terminer
3 vidéos (Total 52 min)
3 vidéos
Maximum Likelihood for Conditional Random Fields13 min
MAP Estimation for MRFs and CRFs9 min
1 exercice pour s'entraîner
Parameter Estimation in MNs30 min
18 heures pour terminer
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.
18 heures pour terminer
7 vidéos (Total 106 min)
7 vidéos
Likelihood Scores16 min
BIC and Asymptotic Consistency11 min
Bayesian Scores20 min
Learning Tree Structured Networks12 min
Learning General Graphs: Heuristic Search23 min
Learning General Graphs: Search and Decomposability15 min
2 exercices pour s'entraîner
Structure Scores30 min
Tree Learning and Hill Climbing30 min
22 heures pour terminer
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.
22 heures pour terminer
5 vidéos (Total 83 min)
5 vidéos
Expectation Maximization - Intro16 min
Analysis of EM Algorithm11 min
EM in Practice11 min
Latent Variables22 min
2 exercices pour s'entraîner
Learning with Incomplete Data30 min
Expectation Maximization30 min
Avis
Meilleurs avis pour PROBABILISTIC GRAPHICAL MODELS 3: LEARNING
par SP11 oct. 2020
An amazing course! The assignments and quizzes can be insanely difficult espceially towards the conclusion.. Requires textbook reading and relistening to lectures to gather the nuances.
par LL29 janv. 2018
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.
par ZZ13 févr. 2017
Great course! Very informative course videos and challenging yet rewarding programming assignments. Hope that the mentors can be more helpful in timely responding for questions.
par MV29 avr. 2020
Great course, especially the programming assignments. Textbook is pretty much necessary for some quizzes, definitely for the final one.
À propos du Spécialisation Modèles graphiques probabilistes
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.
Foire Aux Questions
Quand aurai-je accès aux vidéos de cours et aux devoirs ?
À quoi ai-je droit si je m'abonne à cette Spécialisation ?
Is financial aid available?
Learning Outcomes: By the end of this course, you will be able to
D'autres questions ? Visitez le Centre d'Aide pour les Etudiants.
