Videos tagged with Bayesian Learning

We explore a formal and computational characterization of real world regularity using discrete symmetry groups (hierarchy) as a theoretical basis, embedded in a well-defined Bayesian framework. Our existing work on "A Computational Model for Periodic Pattern Perception Based on Frieze and Wallpaper Groups" (TPAMI 2004), 'Near-regular texture analysis and manipulation' (SGIGRAPH 2004), and "A La...

Nonparametric Bayesian methods are a generalization of probabilistic models where the prior distribution can be a stochastic process, a distribution over a possibly uncountably infinite number of random variables. The great flexibility of these methods has led to applications in natural language processing, machine vision, computational biology and other fields. I will introduce Levy processes,...

In this paper we explore the use of Tree Augmented Naive Bayes (TAN) in regression problems where some of the independent variables are continuous and some others are discrete. The proposed solution is based on the approximation of the joint distribution by a Mixture of Truncated Exponentials (MTE). The construction of the TAN structure requires the use of the conditional mutual information, wh...

Although Bayesian methods for Reinforcement Learning can be traced back to the 1960s (Howard's work in Operations Research), Bayesian methods have only been used sporadically in modern Reinforcement Learning. This is in part because non-Bayesian approaches tend to be much simpler to work with. However, recent advances have shown that Bayesian approaches do not need to be as complex as initially...

Although Bayesian methods for Reinforcement Learning can be traced back to the 1960s (Howard's work in Operations Research), Bayesian methods have only been used sporadically in modern Reinforcement Learning. This is in part because non-Bayesian approaches tend to be much simpler to work with. However, recent advances have shown that Bayesian approaches do not need to be as complex as initially...

Although Bayesian methods for Reinforcement Learning can be traced back to the 1960s (Howard's work in Operations Research), Bayesian methods have only been used sporadically in modern Reinforcement Learning. This is in part because non-Bayesian approaches tend to be much simpler to work with. However, recent advances have shown that Bayesian approaches do not need to be as complex as initially...

The General Systems Architecture Since the summer of 2007, I have been assembling my thoughts and programs on systems, machine learning, distributed programming, and problem solving in general. The meaning of these efforts, for me, is to 1) learn what I can about problem solving, 2) apply my education in formal systems, and 3) use these formal systems in solving real-world problems. What this l...

Bayesian nonparametric models have garnered significant attention in recent years in both the machine learning and statistics communities. These are highly flexible models whose complexity grows with the amount of data, and are nice approaches to addressing the common problem of model selection. In this talk I shall first give a brief overview of Dirichlet processes and infinite mixture models,...

In everyday learning and reasoning, people routinely draw successful generalizations from very limited evidence. Even young children can infer the meanings of words, hidden properties of objects, or the existence of causal relations from just one or a few relevant observations -- far outstripping the capabilities of conventional learning machines. How do they do it? And how can we bring machine...

Lecture slides: Shrinkage Estimator for Bayesian Network Parameters Outline High-Level Overview Neuroimaging Application Find Correlations Among RVs Model with Bayesian Networks Bayesian Network Model Selection Parameterizing Bayesian Networks Laplacian Smoothing Shrinkage ROI Hierarchy How Much to Smooth? Calculating Mixture Weights Mixing Weights for Neuroimaging Data Results Simulated Data R...