People apply Bayesian methods in many areas: from game development to drug discovery. They give superpowers to many machine learning algorithms: handling missing data, extracting much more information from small datasets. Bayesian methods also allow us to estimate uncertainty in predictions, which is a desirable feature for fields like medicine.
Ce cours fait partie de la Spécialisation Apprentissage automatique avancé
Offert par
Spécialisation Apprentissage automatique avancéUniversité nationale de recherche, École des hautes études en sciences économiquesÀ propos de ce cours
74,535 consultations récentes
Résultats de carrière des étudiants
38%
ont commencé une nouvelle carrière après avoir terminé ce cours
24%
ont bénéficié d'un avantage concret dans leur carrières grâce à ce cours
Certificat partageable
Obtenez un Certificat lorsque vous terminez
100 % en ligne
Commencez dès maintenant et apprenez aux horaires qui vous conviennent.
Cours 3 sur 7 dans le
Dates limites flexibles
Réinitialisez les dates limites selon votre disponibilité.
Niveau avancé
Course requires strong background in calculus, linear algebra, probability theory and machine learning.
Approx. 33 heures pour terminer
Anglais
Sous-titres : Arabe, Français, Portugais (européen), Chinois (simplifié), Italien, Vietnamien, Coréen, Allemand, Russe, Turc, Anglais, Espagnol
Compétences que vous acquerrez
Bayesian OptimizationGaussian ProcessMarkov Chain Monte Carlo (MCMC)Variational Bayesian Methods
Résultats de carrière des étudiants
38%
ont commencé une nouvelle carrière après avoir terminé ce cours
24%
ont bénéficié d'un avantage concret dans leur carrières grâce à ce cours
Certificat partageable
Obtenez un Certificat lorsque vous terminez
100 % en ligne
Commencez dès maintenant et apprenez aux horaires qui vous conviennent.
Cours 3 sur 7 dans le
Dates limites flexibles
Réinitialisez les dates limites selon votre disponibilité.
Niveau avancé
Course requires strong background in calculus, linear algebra, probability theory and machine learning.
Approx. 33 heures pour terminer
Anglais
Sous-titres : Arabe, Français, Portugais (européen), Chinois (simplifié), Italien, Vietnamien, Coréen, Allemand, Russe, Turc, Anglais, Espagnol
Offert par
Université nationale de recherche, École des hautes études en sciences économiques
National Research University - Higher School of Economics (HSE) is one of the top research universities in Russia. Established in 1992 to promote new research and teaching in economics and related disciplines, it now offers programs at all levels of university education across an extraordinary range of fields of study including business, sociology, cultural studies, philosophy, political science, international relations, law, Asian studies, media and communicamathematics, engineering, and more.
Programme du cours : ce que vous apprendrez dans ce cours
3 heures pour terminer
Introduction to Bayesian methods & Conjugate priors
Welcome to first week of our course! Today we will discuss what bayesian methods are and what are probabilistic models. We will see how they can be used to model real-life situations and how to make conclusions from them. We will also learn about conjugate priors — a class of models where all math becomes really simple.
3 heures pour terminer
10 vidéos (Total 57 min), 3 lectures, 2 quiz
10 vidéos
About the University1 min
Think bayesian & Statistics review7 min
Bayesian approach to statistics5 min
How to define a model3 min
Example: thief & alarm11 min
Linear regression10 min
Analytical inference3 min
Conjugate distributions2 min
Example: Normal, precision5 min
Example: Bernoulli4 min
3 lectures
About the University10 min
Rules on the academic integrity in the course10 min
MLE estimation of Gaussian mean10 min
2 exercices pour s'entraîner
Introduction to Bayesian methods30 min
Conjugate priors30 min
7 heures pour terminer
Expectation-Maximization algorithm
This week we will about the central topic in probabilistic modeling: the Latent Variable Models and how to train them, namely the Expectation Maximization algorithm. We will see models for clustering and dimensionality reduction where Expectation Maximization algorithm can be applied as is. In the following weeks, we will spend weeks 3, 4, and 5 discussing numerous extensions to this algorithm to make it work for more complicated models and scale to large datasets.
7 heures pour terminer
17 vidéos (Total 168 min)
17 vidéos
Latent Variable Models11 min
Probabilistic clustering6 min
Gaussian Mixture Model10 min
Training GMM10 min
Example of GMM training10 min
Jensen's inequality & Kullback Leibler divergence9 min
Expectation-Maximization algorithm10 min
E-step details12 min
M-step details6 min
Example: EM for discrete mixture, E-step10 min
Example: EM for discrete mixture, M-step12 min
Summary of Expectation Maximization6 min
General EM for GMM12 min
K-means from probabilistic perspective9 min
K-means, M-step7 min
Probabilistic PCA13 min
EM for Probabilistic PCA7 min
2 exercices pour s'entraîner
EM algorithm30 min
Latent Variable Models and EM algorithm30 min
2 heures pour terminer
Variational Inference & Latent Dirichlet Allocation
This week we will move on to approximate inference methods. We will see why we care about approximating distributions and see variational inference — one of the most powerful methods for this task. We will also see mean-field approximation in details. And apply it to text-mining algorithm called Latent Dirichlet Allocation
2 heures pour terminer
11 vidéos (Total 98 min)
11 vidéos
Mean field approximation13 min
Example: Ising model15 min
Variational EM & Review5 min
Topic modeling5 min
Dirichlet distribution6 min
Latent Dirichlet Allocation5 min
LDA: E-step, theta11 min
LDA: E-step, z8 min
LDA: M-step & prediction13 min
Extensions of LDA5 min
2 exercices pour s'entraîner
Variational inference15 min
Latent Dirichlet Allocation15 min
6 heures pour terminer
Markov chain Monte Carlo
This week we will learn how to approximate training and inference with sampling and how to sample from complicated distributions. This will allow us to build simple method to deal with LDA and with Bayesian Neural Networks — Neural Networks which weights are random variables themselves and instead of training (finding the best value for the weights) we will sample from the posterior distributions on weights.
6 heures pour terminer
11 vidéos (Total 122 min)
11 vidéos
Monte Carlo estimation12 min
Sampling from 1-d distributions13 min
Markov Chains13 min
Gibbs sampling12 min
Example of Gibbs sampling7 min
Metropolis-Hastings8 min
Metropolis-Hastings: choosing the critic8 min
Example of Metropolis-Hastings9 min
Markov Chain Monte Carlo summary8 min
MCMC for LDA15 min
Bayesian Neural Networks11 min
1 exercice pour s'entraîner
Markov Chain Monte Carlo30 min
Avis
Meilleurs avis pour BAYESIAN METHODS FOR MACHINE LEARNING
par JG17 nov. 2017
This course is little difficult. But I could find very helpful. Also, I didn't find better course on Bayesian anywhere on the net. So I will recommend this if anyone wants to die into bayesian.
par HR18 juin 2018
It probably offers the most comprehensive overview of Bayesian methods online. However, it would be nice these methods translate into practical data science problems found in the industry.
par LB6 juin 2019
Excellent course! The perfect balance of clear and relevant material and challenging but reasonable exercises. My only critique would be that one of the lecturers sounds very sleepy.
par C29 janv. 2020
The course covers a lot of very advanced material and is a great starting point for Bayesian Methods, but it would greatly benefit from having additional reading materials.
À propos du Spécialisation Apprentissage automatique avancé
This specialization gives an introduction to deep learning, reinforcement learning, natural language understanding, computer vision and Bayesian methods. Top Kaggle machine learning practitioners and CERN scientists will share their experience of solving real-world problems and help you to fill the gaps between theory and practice. Upon completion of 7 courses you will be able to apply modern machine learning methods in enterprise and understand the caveats of real-world data and settings.
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?
What background knowledge is necessary?
Puis-je obtenir des crédits universitaires si je réussis le Cours ?
D'autres questions ? Visitez le Centre d'Aide pour les Etudiants.
