Informações sobre o curso: 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 first in a sequence of three. It describes the two basic PGM representations: Bayesian Networks, which rely on a directed graph; and Markov networks, which use an undirected graph. The course discusses both the theoretical properties of these representations as well as their use in practice. The (highly recommended) honors track contains several hands-on assignments on how to represent some real-world problems. The course also presents some important extensions beyond the basic PGM representation, which allow more complex models to be encoded compactly.

Desenvolvido por: Universidade de Stanford

Ministrado por: Daphne Koller, Professor
School of Engineering

Informações básicas	Curso 1 de 3 no Probabilistic Graphical Models Specialization
Nível	Advanced
Idioma	English
Como ser aprovado	Seja aprovado em todas as tarefas para concluir o curso.
Classificação do usuário	4.7 estrelas Classificação média do usuário 4.7Veja o que os aprendizes disseram

Programa

SEMANA 1

Introduction and Overview

This module provides an overall introduction to probabilistic graphical models, and defines a few of the key concepts that will be used later in the course.

4 vídeos

Vídeo: Welcome!
Vídeo: Overview and Motivation
Vídeo: Distributions
Vídeo: Factors

Nota atribuída: Basic Definitions

Bayesian Network (Directed Models)

In this module, we define the Bayesian network representation and its semantics. We also analyze the relationship between the graph structure and the independence properties of a distribution represented over that graph. Finally, we give some practical tips on how to model a real-world situation as a Bayesian network.

15 vídeos, 6 leituras

Vídeo: Semantics & Factorization
Vídeo: Reasoning Patterns
Vídeo: Flow of Probabilistic Influence
Vídeo: Conditional Independence
Vídeo: Independencies in Bayesian Networks
Vídeo: Naive Bayes
Vídeo: Application - Medical Diagnosis
Vídeo: Knowledge Engineering Example - SAMIAM
Reading: Setting Up Your Programming Assignment Environment
Reading: Installing Octave/MATLAB on Windows
Reading: Installing Octave/MATLAB on Mac OS X (10.10 Yosemite and 10.9 Mavericks)
Reading: Installing Octave/MATLAB on Mac OS X (10.8 Mountain Lion and Earlier)
Reading: Installing Octave/MATLAB on GNU/Linux
Reading: More Octave/MATLAB resources
Vídeo: Basic Operations
Vídeo: Moving Data Around
Vídeo: Computing On Data
Vídeo: Plotting Data
Vídeo: Control Statements: for, while, if statements
Vídeo: Vectorization
Vídeo: Working on and Submitting Programming Exercises

Nota atribuída: Bayesian Network Fundamentals

Nota atribuída: Bayesian Network Independencies

Nota atribuída: Octave/Matlab installation

Nota atribuída: Simple BN Knowledge Engineering

SEMANA 2

Template Models for Bayesian Networks

In many cases, we need to model distributions that have a recurring structure. In this module, we describe representations for two such situations. One is temporal scenarios, where we want to model a probabilistic structure that holds constant over time; here, we use Hidden Markov Models, or, more generally, Dynamic Bayesian Networks. The other is aimed at scenarios that involve multiple similar entities, each of whose properties is governed by a similar model; here, we use Plate Models.

4 vídeos

Vídeo: Overview of Template Models
Vídeo: Temporal Models - DBNs
Vídeo: Temporal Models - HMMs
Vídeo: Plate Models

Nota atribuída: Template Models

Structured CPDs for Bayesian Networks

A table-based representation of a CPD in a Bayesian network has a size that grows exponentially in the number of parents. There are a variety of other form of CPD that exploit some type of structure in the dependency model to allow for a much more compact representation. Here we describe a number of the ones most commonly used in practice.

4 vídeos

Vídeo: Overview: Structured CPDs
Vídeo: Tree-Structured CPDs
Vídeo: Independence of Causal Influence
Vídeo: Continuous Variables

Nota atribuída: Structured CPDs

Nota atribuída: BNs for Genetic Inheritance

Nota atribuída: BNs for Genetic Inheritance PA Quiz

SEMANA 3

Markov Networks (Undirected Models)

In this module, we describe Markov networks (also called Markov random fields): probabilistic graphical models based on an undirected graph representation. We discuss the representation of these models and their semantics. We also analyze the independence properties of distributions encoded by these graphs, and their relationship to the graph structure. We compare these independencies to those encoded by a Bayesian network, giving us some insight on which type of model is more suitable for which scenarios.

7 vídeos

Vídeo: Pairwise Markov Networks
Vídeo: General Gibbs Distribution
Vídeo: Conditional Random Fields
Vídeo: Independencies in Markov Networks
Vídeo: I-maps and perfect maps
Vídeo: Log-Linear Models
Vídeo: Shared Features in Log-Linear Models

Nota atribuída: Markov Networks

Nota atribuída: Independencies Revisited

Nota atribuída: Markov Networks for OCR

SEMANA 4

Decision Making

In this module, we discuss the task of decision making under uncertainty. We describe the framework of decision theory, including some aspects of utility functions. We then talk about how decision making scenarios can be encoded as a graphical model called an Influence Diagram, and how such models provide insight both into decision making and the value of information gathering.

3 vídeos

Vídeo: Maximum Expected Utility
Vídeo: Utility Functions
Vídeo: Value of Perfect Information

Nota atribuída: Decision Theory

Nota atribuída: Decision Making

Nota atribuída: Decision Making PA Quiz

SEMANA 5

Knowledge Engineering & Summary

This module provides an overview of graphical model representations and some of the real-world considerations when modeling a scenario as a graphical model. It also includes the course final exam.

1 vídeo

Vídeo: Knowledge Engineering

Nota atribuída: Representation Final Exam

Perguntas frequentes

When will I have access to the lectures and assignments?

What will I get if I pay for this course?

What is the refund policy?

Is financial aid available?

Learning Outcomes: By the end of this course, you will be able to

Como funciona

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.

Desenvolvedores

Universidade 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.

Custo

	Comprar curso
Acesso aos materiais do curso	Disponível
Acesso a materiais valendo nota	Disponível
Receba uma nota final	Disponível
Obtenha um Certificado de Curso compartilhável	Disponível

Classificações e avaliações

Avaliado em 4.7 de 5 decorrente de 762 avaliações

very good, practical.

This is not an easy course, so beware. The instruction is solid but you still need to reason through a lot on your own, and especially if you choose to complete the Honors programming section (which I highly recommend to prove to yourself that you really understand what you have learned and can apply it), you really need to plan on allocating sufficient number of hours to work through the programming assignments. You'll likely need to re-watch several of the video segments several times for it to really sink in, as well as referencing the Discussion Forum when you are stuck and need inspiration. Once you do complete this course (after many hours of work and thought) you will enjoy a deep sense of accomplishment, will look and think about decision-making in a fresh new way, and have learned many very useful skills.

The course helps me understand what a probabilistic graphical model is and how and why it works. One aspect I like the most about the course is the programming assignments. Those PA really make a lot of concepts clearer although sometimes you need to think carefully when the instruction is hard to follow. I think there should be more test case and expected results so that students know what is asked and to evaluate their own code. The instructor is generally clear but sometimes she goes too fast on certain concept. The course is hard but if you gives in time and effort you can complete it.