Results 1  10
of
39
Hierarchical Bayesian Inference in the Visual Cortex
, 2002
"... this paper, we propose a Bayesian theory of hierarchical cortical computation based both on (a) the mathematical and computational ideas of computer vision and pattern the ory and on (b) recent neurophysiological experimental evidence. We ,2 have proposed that Grenander's pattern theory 3 coul ..."
Abstract

Cited by 296 (2 self)
 Add to MetaCart
this paper, we propose a Bayesian theory of hierarchical cortical computation based both on (a) the mathematical and computational ideas of computer vision and pattern the ory and on (b) recent neurophysiological experimental evidence. We ,2 have proposed that Grenander's pattern theory 3 could potentially model the brain as a generafive model in such a way that feedback serves to disambiguate and 'explain away' the earlier representa tion. The Helmholtz machine 4, 5 was an excellent step towards approximating this proposal, with feedback implementing priors. Its development, however, was rather limited, dealing only with binary images. Moreover, its feedback mechanisms were engaged only during the learning of the feedforward connections but not during perceptual inference, though the Gibbs sampling process for inference can potentially be interpreted as topdown feedback disambiguating low level representations? Rao and Ballard's predictive coding/Kalman filter model 6 did integrate generafive feedback in the perceptual inference process, but it was primarily a linear model and thus severely limited in practical utility. The datadriven Markov Chain Monte Carlo approach of Zhu and colleagues 7, 8 might be the most successful recent application of this proposal in solving real and difficult computer vision problems using generafive models, though its connection to the visual cortex has not been explored. Here, we bring in a powerful and widely applicable paradigm from artificial intelligence and computer vision to propose some new ideas about the algorithms of visual cortical process ing and the nature of representations in the visual cortex. We will review some of our and others' neurophysiological experimental data to lend support to these ideas
The Role of the Primary Visual Cortex in Higher Level Vision
, 1998
"... In the classical feedforward, modular view of visual processing, the primary visual cortex (area V1) is a module that serves to extract local features such as edges and bars. Representation and recognition of objects are thought to be functions of higher extrastriate cortical areas. This paper pres ..."
Abstract

Cited by 166 (8 self)
 Add to MetaCart
In the classical feedforward, modular view of visual processing, the primary visual cortex (area V1) is a module that serves to extract local features such as edges and bars. Representation and recognition of objects are thought to be functions of higher extrastriate cortical areas. This paper presents neurophysiological data that show the later part of V1 neurons' responses reflecting higher order perceptual computations related to Ullman's (Cognition 1984;18:97  159) visual routines and Marr's (Vision NJ: Freeman 1982) full primal sketch, 2 1 2 D sketch and 3D model. Based on theoretical reasoning and the experimental evidence, we propose a possible reinterpretation of the functional role of V1. In this framework, because of V1 neurons' precise encoding of orientation and spatial information, higher level perceptual computations and representations that involve high resolution details, fine geometry and spatial precision would necessarily involve V1 and be reflected in the later...
Local Learning in Probabilistic Networks With Hidden Variables
, 1995
"... Probabilistic networks, which provide compact descriptions of complex stochastic relationships among several random variables, are rapidly becoming the tool of choice for uncertain reasoning in artificial intelligence. We show that networks with fixed structure containing hidden variables can be lea ..."
Abstract

Cited by 83 (5 self)
 Add to MetaCart
Probabilistic networks, which provide compact descriptions of complex stochastic relationships among several random variables, are rapidly becoming the tool of choice for uncertain reasoning in artificial intelligence. We show that networks with fixed structure containing hidden variables can be learned automatically from data using a gradientdescent mechanism similar to that used in neural networks. We also extend the method to networks with intensionally represented distributions, including networks with continuous variables and dynamic probabilistic networks. Because probabilistic networks provide explicit representations of causal structure, human experts can easily contribute prior knowledge to the training process, thereby significantly improving the learning rate. Adaptive probabilistic networks (APNs) may soon compete directly with neural networks as models in computational neuroscience as well as in industrial and financial applications. 1 Introduction Intelligent systems, ...
A Nonparametric MultiScale Statistical Model for Natural Images
 Advances in Neural Information Processing
, 1997
"... The observed distribution of natural images is far from uniform. On the contrary, real images have complex and important structure that can be exploited for image processing, recognition and analysis. There have been many proposed approaches to the principled statistical modeling of images, but each ..."
Abstract

Cited by 81 (2 self)
 Add to MetaCart
The observed distribution of natural images is far from uniform. On the contrary, real images have complex and important structure that can be exploited for image processing, recognition and analysis. There have been many proposed approaches to the principled statistical modeling of images, but each has been limited in either the complexity of the models or the complexity of the images. We present a nonparametric multiscale statistical model for images that can be used for recognition, image denoising, and in a "generative mode" to synthesize high quality textures. Accepted Advanced in Neural Information Processing 10 (1997). 1 Introduction In this paper we describe a multiscale statistical model which can capture the structure of natural images across many scales. Once trained on example images, it can be used to recognize novel images, or to generate new images. Each of these tasks is reasonably efficient, requiring no more than a few seconds or minutes on a workstation. The sta...
Recognizing handwritten digits using mixtures of linear models
 Advances in Neural Information Processing Systems 7
, 1995
"... We construct a mixture of locally linear generative models of a collection of pixelbased images of digits, and use them for recognition. Different models of a given digit are used to capture different styles of writing, and new images are classified by evaluating their loglikelihoods under each mo ..."
Abstract

Cited by 64 (6 self)
 Add to MetaCart
(Show Context)
We construct a mixture of locally linear generative models of a collection of pixelbased images of digits, and use them for recognition. Different models of a given digit are used to capture different styles of writing, and new images are classified by evaluating their loglikelihoods under each model. We use an EMbased algorithm in which the Mstep is computationally straightforward principal components analysis (PCA). Incorporating tangentplane information [12] about expected local deformations only requires adding tangent vectors into the sample covariance matrices for the PCA, and it demonstrably improves performance. 1
Developments in Probabilistic Modelling with Neural Networks  Ensemble Learning
"... Ensemble learning by vmiational free energy minimization is a framework for statistical inference in which aa ensemble of parameter vectors is optimized rather thaa a single parameter vector. The ensemble approximates the posterior probability distribution of the parameters. ..."
Abstract

Cited by 56 (5 self)
 Add to MetaCart
Ensemble learning by vmiational free energy minimization is a framework for statistical inference in which aa ensemble of parameter vectors is optimized rather thaa a single parameter vector. The ensemble approximates the posterior probability distribution of the parameters.
Stochastic backpropagation and approximate inference in deep generative models
, 2014
"... We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a recognition model to represent an approximate posterior distri ..."
Abstract

Cited by 25 (3 self)
 Add to MetaCart
(Show Context)
We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a recognition model to represent an approximate posterior distribution and uses this for optimisation of a variational lower bound. We develop stochastic backpropagation – rules for gradient backpropagation through stochastic variables – and derive an algorithm that allows for joint optimisation of the parameters of both the generative and recognition models. We demonstrate on several realworld data sets that by using stochastic backpropagation and variational inference, we obtain models that are able to generate realistic samples of data, allow for accurate imputations of missing data, and provide a useful tool for highdimensional data visualisation. 1.
Ensemble Learning and Evidence Maximization
 Proc. NIPS
, 1995
"... Ensemble learning by variational free energy minimization is a tool introduced to neural networks by Hinton and van Camp in which learning is described in terms of the optimization of an ensemble of parameter vectors. The optimized ensemble is an approximation to the posterior probability distributi ..."
Abstract

Cited by 22 (1 self)
 Add to MetaCart
(Show Context)
Ensemble learning by variational free energy minimization is a tool introduced to neural networks by Hinton and van Camp in which learning is described in terms of the optimization of an ensemble of parameter vectors. The optimized ensemble is an approximation to the posterior probability distribution of the parameters. This tool has now been applied to a variety of statistical inference problems. In this paper I study a linear regression model with both parameters and hyperparameters. I demonstrate that the evidence approximation for the optimization of regularization constants can be derived in detail from a free energy minimization viewpoint. 1 Ensemble Learning by Free Energy Minimization A new tool has recently been introduced into the field of neural networks and statistical inference. In traditional approaches to neural networks, a single parameter vector w is optimized by maximum likelihood or penalized maximum likelihood. In the Bayesian interpretation, these optimized param...
Neural Variational Inference and Learning in Belief Networks
"... Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied to them scale well. We propose a fast noniterative appr ..."
Abstract

Cited by 19 (1 self)
 Add to MetaCart
(Show Context)
Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied to them scale well. We propose a fast noniterative approximate inference method that uses a feedforward network to implement efficient exact sampling from the variational posterior. The model and this inference network are trained jointly by maximizing a variational lower bound on the loglikelihood. Although the naive estimator of the inference network gradient is too highvariance to be useful, we make it practical by applying several straightforward modelindependent variance reduction techniques. Applying our approach to training sigmoid belief networks and deep autoregressive networks, we show that it outperforms the wakesleep algorithm on MNIST and achieves stateoftheart results on the Reuters RCV1 document dataset. 1.
ACh, uncertainty, and cortical inference
 Advances in Neural Information Processing Systems 14:189–196
, 2002
"... Acetylcholine (ACh) has been implicated in a wide variety of tasks involving attentional processes and plasticity. Following extensive animal studies, it has previously been suggested that ACh reports on uncertainty and controls hippocampal, cortical and corticoamygdalar plasticity. We extend this ..."
Abstract

Cited by 9 (7 self)
 Add to MetaCart
Acetylcholine (ACh) has been implicated in a wide variety of tasks involving attentional processes and plasticity. Following extensive animal studies, it has previously been suggested that ACh reports on uncertainty and controls hippocampal, cortical and corticoamygdalar plasticity. We extend this view and consider its effects on cortical representational inference, arguing that ACh controls the balance between bottomup inference, influenced by input stimuli, and topdown inference, influenced by contextual information. We illustrate our proposal using a hierarchical hidden Markov model. 1