Results 1  10
of
49
What and where: A Bayesian inference theory of attention
, 2010
"... In the theoretical framework described in this thesis, attention is part of the inference process that solves the visual recognition problem of what is where. The theory proposes a computational role for attention and leads to a model that predicts some of its main properties at the level of psychop ..."
Abstract

Cited by 35 (6 self)
 Add to MetaCart
In the theoretical framework described in this thesis, attention is part of the inference process that solves the visual recognition problem of what is where. The theory proposes a computational role for attention and leads to a model that predicts some of its main properties at the level of psychophysics and physiology. In our approach, the main goal of the visual system is to infer the identity and the position of objects in visual scenes: spatial attention emerges as a strategy to reduce the uncertainty in shape information while featurebased attention reduces the uncertainty in spatial information. Featural and spatial attention represent two distinct modes of a computational process solving the problem of recognizing and localizing objects, especially in difficult recognition tasks such as in cluttered natural scenes. We describe a specific computational model and relate it to the known functional anatomy of attention. We show that several wellknown attentional phenomena – including bottomup popout effects, multiplicative modulation of neuronal tuning
How the brain might work: A hierarchical and temporal model for learning and recognition
 STANFORD UNIVERSITY
, 2008
"... ..."
(Show Context)
Two DistributedState Models For Generating HighDimensional Time Series
, 2011
"... In this paper we develop a class of nonlinear generative models for highdimensional time series. We first propose a model based on the restricted Boltzmann machine (RBM) that uses an undirected model with binary latent variables and realvalued “visible” variables. The latent and visible variables ..."
Abstract

Cited by 12 (1 self)
 Add to MetaCart
(Show Context)
In this paper we develop a class of nonlinear generative models for highdimensional time series. We first propose a model based on the restricted Boltzmann machine (RBM) that uses an undirected model with binary latent variables and realvalued “visible” variables. The latent and visible variables at each time step receive directed connections from the visible variables at the last few timesteps. This “conditional” RBM (CRBM) makes online inference efficient and allows us to use a simple approximate learning procedure. We demonstrate the power of our approach by synthesizing various sequences from a model trained on motion capture data and by performing online filling in of data lost during capture. We extend the CRBM in a way that preserves its most important computational properties and introduces multiplicative threeway interactions that allow the effective interaction weight between two variables to be modulated by the dynamic state of a third variable. We introduce a factoring of the implied threeway weight tensor to permit a more compact parameterization. The resulting model can capture diverse styles of motion with a single set of parameters, and the threeway interactions greatly improve its ability to blend motion styles or to transition smoothly among them. Videos and source code can be found at
Discovering Binary Codes for Documents by Learning Deep Generative Models
, 2010
"... We describe a deep generative model in which the lowest layer represents the wordcount vector of a document and the top layer represents a learned binary code for that document. The top two layers of the generative model form an undirected associative memory and the remaining layers form a belief n ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
We describe a deep generative model in which the lowest layer represents the wordcount vector of a document and the top layer represents a learned binary code for that document. The top two layers of the generative model form an undirected associative memory and the remaining layers form a belief net with directed, topdown connections. We present efficient learning and inference procedures for this type of generative model and show that it allows more accurate and much faster retrieval than latent semantic analysis. By using our method as a filter for a much slower method called TFIDF we achieve higher accuracy than TFIDF alone and save several orders of magnitude in retrieval time. By using short binary codes as addresses, we can perform retrieval on very large document sets in a time that is independent of the size of the document set using only one word of memory to describe each document.
Convex Sparse Coding, Subspace Learning, and SemiSupervised Extensions
"... Automated feature discovery is a fundamental problem in machine learning. Although classical feature discovery methods do not guarantee optimal solutions in general, it has been recently noted that certain subspace learning and sparse coding problems can be solved efficiently, provided the number of ..."
Abstract

Cited by 10 (3 self)
 Add to MetaCart
Automated feature discovery is a fundamental problem in machine learning. Although classical feature discovery methods do not guarantee optimal solutions in general, it has been recently noted that certain subspace learning and sparse coding problems can be solved efficiently, provided the number of features is not restricted a priori. We provide an extended characterization of this optimality result and describe the nature of the solutions under an expanded set of practical contexts. In particular, we apply the framework to a semisupervised learning problem, and demonstrate that feature discovery can cooccur with input reconstruction and supervised training while still admitting globally optimal solutions. A comparison to existing semisupervised feature discovery methods shows improved generalization and efficiency.
Independent Component Analysis: Recent Advances
"... Independent component analysis is a probabilistic method for learning a linear transform of a random vector. The goal is to find components which are maximally independent and nonGaussian (nonnormal). Its fundamental difference to classical multivariate statistical methods is in the assumption of ..."
Abstract

Cited by 9 (0 self)
 Add to MetaCart
(Show Context)
Independent component analysis is a probabilistic method for learning a linear transform of a random vector. The goal is to find components which are maximally independent and nonGaussian (nonnormal). Its fundamental difference to classical multivariate statistical methods is in the assumption of nonGaussianity, which enables the identification of original, underlying components, in contrast to classical methods. The basic theory of ICA was mainly developed in the 1990’s and summarized, for example, in our monograph in 2001. Here, we provide an overview of some recent developments in the theory since the year 2000. The main topics are: analysis of causal relations, testing independent components, analysing multiple data sets (threeway data), modelling dependencies between the components, and improved methods for estimating the basic model. Key words: independent component analysis, blind source separation, nonGaussianity, causal analysis. 1.
Learning Hierarchical Compositional Representations of Object Structure
"... Visual categorization of objects has captured the attention of the vision community for decades [10]. The increased popularity of the problem witnessed in the recent years and the advent of powerful computer hardware have led to a seeming success of categorization approaches on the standard datasets ..."
Abstract

Cited by 9 (3 self)
 Add to MetaCart
(Show Context)
Visual categorization of objects has captured the attention of the vision community for decades [10]. The increased popularity of the problem witnessed in the recent years and the advent of powerful computer hardware have led to a seeming success of categorization approaches on the standard datasets such as
What and where: a bayesian inference theory of visual attention
 Vision Research
"... In the theoretical framework described in this thesis, attention is part of the inference process that solves the visual recognition problem of what is where. The theory proposes a computational role for attention and leads to a model that predicts some of its main properties at the level of psych ..."
Abstract

Cited by 5 (1 self)
 Add to MetaCart
(Show Context)
In the theoretical framework described in this thesis, attention is part of the inference process that solves the visual recognition problem of what is where. The theory proposes a computational role for attention and leads to a model that predicts some of its main properties at the level of psychophysics and physiology. In our approach, the main goal of the visual system is to infer the identity and the position of objects in visual scenes: spatial attention emerges as a strategy to reduce the uncertainty in shape information while featurebased attention reduces the uncertainty in spatial information. Featural and spatial attention represent two distinct modes of a computational process solving the problem of recognizing and localizing objects, especially in difficult recognition tasks such as in cluttered natural scenes. We describe a specific computational model and relate it to the known functional anatomy of attention. We show that several wellknown attentional phenomena including bottomup popout effects, multiplicative modulation of neuronal tuning curves and shift in contrast responses emerge naturally as predictions of the model. We also show that the bayesian model predicts well human eye fixations (considered as a proxy