Results 1  10
of
167
CONDENSATION  conditional density propagation for visual tracking
 International Journal of Computer Vision
, 1998
"... The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimodal, cannot represent simultaneous alternative hypotheses. The Condensation algorithm uses "factored sampling", previously applied to the ..."
Abstract

Cited by 1124 (12 self)
 Add to MetaCart
The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimodal, cannot represent simultaneous alternative hypotheses. The Condensation algorithm uses "factored sampling", previously applied to the interpretation of static images, in which the probability distribution of possible interpretations is represented by a randomly generated set. Condensation uses learned dynamical models, together with visual observations, to propagate the random set over time. The result is highly robust tracking of agile motion. Notwithstanding the use of stochastic methods, the algorithm runs in near realtime. Contents 1 Tracking curves in clutter 2 2 Discretetime propagation of state density 3 3 Factored sampling 6 4 The Condensation algorithm 8 5 Stochastic dynamical models for curve motion 10 6 Observation model 13 7 Applying the Condensation algorithm to videostreams 17 8 Conclusions 26 A Nonline...
Contour Tracking By Stochastic Propagation of Conditional Density
, 1996
"... . In Proc. European Conf. Computer Vision, 1996, pp. 343356, Cambridge, UK The problem of tracking curves in dense visual clutter is a challenging one. Trackers based on Kalman filters are of limited use; because they are based on Gaussian densities which are unimodal, they cannot represent s ..."
Abstract

Cited by 565 (23 self)
 Add to MetaCart
. In Proc. European Conf. Computer Vision, 1996, pp. 343356, Cambridge, UK The problem of tracking curves in dense visual clutter is a challenging one. Trackers based on Kalman filters are of limited use; because they are based on Gaussian densities which are unimodal, they cannot represent simultaneous alternative hypotheses. Extensions to the Kalman filter to handle multiple data associations work satisfactorily in the simple case of point targets, but do not extend naturally to continuous curves. A new, stochastic algorithm is proposed here, the Condensation algorithm  Conditional Density Propagation over time. It uses `factored sampling', a method previously applied to interpretation of static images, in which the distribution of possible interpretations is represented by a randomly generated set of representatives. The Condensation algorithm combines factored sampling with learned dynamical models to propagate an entire probability distribution for object pos...
ANFIS: AdaptiveNetworkBased Fuzzy Inference System
, 1993
"... This paper presents the architecture and learning procedure underlying ANFIS (AdaptiveNetwork based Fuzzy Inference System), a fuzzy inference system implemented in the framework of adaptive networks. By using a hybrid learning procedure, the proposed ANFIS can construct an inputoutput mapping bas ..."
Abstract

Cited by 432 (5 self)
 Add to MetaCart
This paper presents the architecture and learning procedure underlying ANFIS (AdaptiveNetwork based Fuzzy Inference System), a fuzzy inference system implemented in the framework of adaptive networks. By using a hybrid learning procedure, the proposed ANFIS can construct an inputoutput mapping based on both human knowledge (in the form of fuzzy ifthen rules) and stipulated inputoutput data pairs. In our simulation, we employ the ANFIS architecture to model nonlinear functions, identify nonlinear components onlinely in a control system, and predict a chaotic time series, all yielding remarkable results. Comparisons with artificail neural networks and earlier work on fuzzy modeling are listed and discussed. Other extensions of the proposed ANFIS and promising applications to automatic control and signal processing are also suggested. 1 Introduction System modeling based on conventional mathematical tools (e.g., differential equations) is not well suited for dealing with illdefine...
A ControlTheoretic Approach to Flow Control
, 1991
"... This paper presents a controltheoretic approach to reactive flow control in networks that do not reserve bandwidth. We assume a roundrobinlike queue service discipline in the output queues of the network’s switches, and propose deterministic and stochastic models for a single conversation in a ne ..."
Abstract

Cited by 380 (7 self)
 Add to MetaCart
This paper presents a controltheoretic approach to reactive flow control in networks that do not reserve bandwidth. We assume a roundrobinlike queue service discipline in the output queues of the network’s switches, and propose deterministic and stochastic models for a single conversation in a network of such switches. These models motivate the PacketPair rate probing technique, and a provably stable ratebased flow control scheme. A Kalman state estimator is derived from discretetime state space analysis, but there are difficulties in using the estimator in practice. These difficulties are overcome by a novel estimation scheme based on fuzzy logic. We then present a technique to extract and use additional information horn the system to develop a continuoustime system model. This is used to design a wuisnt of the control law that is also provably stable, and, in addition, takes control action as rapidly as possible. Finally, practical issues such as correcting parameter drift and cmmlination with window flow control are described.
Simple statistical gradientfollowing algorithms for connectionist reinforcement learning
 Machine Learning
, 1992
"... Abstract. This article presents a general class of associative reinforcement learning algorithms for connectionist networks containing stochastic units. These algorithms, called REINFORCE algorithms, are shown to make weight adjustments in a direction that lies along the gradient of expected reinfor ..."
Abstract

Cited by 321 (0 self)
 Add to MetaCart
Abstract. This article presents a general class of associative reinforcement learning algorithms for connectionist networks containing stochastic units. These algorithms, called REINFORCE algorithms, are shown to make weight adjustments in a direction that lies along the gradient of expected reinforcement in both immediatereinforcement tasks and certain limited forms of delayedreinforcement tasks, and they do this without explicitly computing gradient estimates or even storing information from which such estimates could be computed. Specific examples of such algorithms are presented, some of which bear a close relationship to certain existing algorithms while others are novel but potentially interesting in their own right. Also given are results that show how such algorithms can be naturally integrated with backpropagation. We close with a brief discussion of a number of additional issues surrounding the use of such algorithms, including what is known about their limiting behaviors as well as further considerations that might be used to help develop similar but potentially more powerful reinforcement learning algorithms.
Forward models: Supervised learning with a distal teacher
 Cognitive Science
, 1992
"... Internal models of the environment have an important role to play in adaptive systems in general and are of particular importance for the supervised learning paradigm. In this paper we demonstrate that certain classical problems associated with the notion of the \teacher " in supervised learnin ..."
Abstract

Cited by 295 (7 self)
 Add to MetaCart
Internal models of the environment have an important role to play in adaptive systems in general and are of particular importance for the supervised learning paradigm. In this paper we demonstrate that certain classical problems associated with the notion of the \teacher " in supervised learning can be solved by judicious use of learned internal models as components of the adaptive system. In particular, we show how supervised learning algorithms can be utilized in cases in which an unknown dynamical system intervenes between actions and desired outcomes. Our approach applies to any supervised learning algorithm that is capable of learning in multilayer networks.
A Unifying Review of Linear Gaussian Models
, 1999
"... Factor analysis, principal component analysis, mixtures of gaussian clusters, vector quantization, Kalman filter models, and hidden Markov models can all be unified as variations of unsupervised learning under a single basic generative model. This is achieved by collecting together disparate observa ..."
Abstract

Cited by 260 (17 self)
 Add to MetaCart
Factor analysis, principal component analysis, mixtures of gaussian clusters, vector quantization, Kalman filter models, and hidden Markov models can all be unified as variations of unsupervised learning under a single basic generative model. This is achieved by collecting together disparate observations and derivations made by many previous authors and introducing a new way of linking discrete and continuous state models using a simple nonlinearity. Through the use of other nonlinearities, we show how independent component analysis is also a variation of the same basic generative model. We show that factor analysis and mixtures of gaussians can be implemented in autoencoder neural networks and learned using squared error plus the same regularization term. We introduce a new model for static data, known as sensible principal component analysis, as well as a novel concept of spatially adaptive observation noise. We also review some of the literature involving global and local mixtures of the basic models and provide pseudocode for inference and learning for all the basic models.
Learning and Sequential Decision Making
 LEARNING AND COMPUTATIONAL NEUROSCIENCE
, 1989
"... In this report we show how the class of adaptive prediction methods that Sutton called "temporal difference," or TD, methods are related to the theory of squential decision making. TD methods have been used as "adaptive critics" in connectionist learning systems, and have been proposed as models of ..."
Abstract

Cited by 195 (10 self)
 Add to MetaCart
In this report we show how the class of adaptive prediction methods that Sutton called "temporal difference," or TD, methods are related to the theory of squential decision making. TD methods have been used as "adaptive critics" in connectionist learning systems, and have been proposed as models of animal learning in classical conditioning experiments. Here we relate TD methods to decision tasks formulated in terms of a stochastic dynamical system whose behavior unfolds over time under the influence of a decision maker's actions. Strategies are sought for selecting actions so as to maximize a measure of longterm payoff gain. Mathematically, tasks such as this can be formulated as Markovian decision problems, and numerous methods have been proposed for learning how to solve such problems. We show how a TD method can be understood as a novel synthesis of concepts from the theory of stochastic dynamic programming, which comprises the standard method for solving such tasks when a model of the dynamical system is available, and the theory of parameter estimation, which provides the appropriate context for studying learning rules in the form of equations for updating associative strengths in behavioral models, or connection weights in connectionist networks. Because this report is oriented primarily toward the nonengineer interested in animal learning, it presents tutorials on stochastic sequential decision tasks, stochastic dynamic programming, and parameter estimation.
Linear leastsquares algorithms for temporal difference learning
 Machine Learning
, 1996
"... Abstract. We introduce two new temporal difference (TD) algorithms based on the theory of linear leastsquares function approximation. We define an algorithm we call LeastSquares TD (LS TD) for which we prove probabilityone convergence when it is used with a function approximator linear in the adju ..."
Abstract

Cited by 182 (0 self)
 Add to MetaCart
Abstract. We introduce two new temporal difference (TD) algorithms based on the theory of linear leastsquares function approximation. We define an algorithm we call LeastSquares TD (LS TD) for which we prove probabilityone convergence when it is used with a function approximator linear in the adjustable parameters. We then define a recursive version of this algorithm, Recursive LeastSquares TD (RLS TD). Although these new TD algorithms require more computation per timestep than do Sutton's TD(A) algorithms, they are more efficient in a statistical sense because they extract more information from training experiences. We describe a simulation experiment showing the substantial improvement in learning rate achieved by RLS TD in an example Markov prediction problem. To quantify this improvement, we introduce the TD error variance of a Markov chain, arc,, and experimentally conclude that the convergence rate of a TD algorithm depends linearly on ~ro. In addition to converging more rapidly, LS TD and RLS TD do not have control parameters, such as a learning rate parameter, thus eliminating the possibility of achieving poor performance by an unlucky choice of parameters.
Computational Models of Sensorimotor Integration
 SCIENCE
, 1997
"... The sensorimotor integration system can be viewed as an observer attempting to estimate its own state and the state of the environment by integrating multiple sources of information. We describe a computational framework capturing this notion, and some specific models of integration and adaptati ..."
Abstract

Cited by 178 (10 self)
 Add to MetaCart
The sensorimotor integration system can be viewed as an observer attempting to estimate its own state and the state of the environment by integrating multiple sources of information. We describe a computational framework capturing this notion, and some specific models of integration and adaptation that result from it. Psychophysical results from two sensorimotor systems, subserving the integration and adaptation of visuoauditory maps, and estimation of the state of the hand during arm movements, are presented and analyzed within this framework. These results suggest that: (1) Spatial information from visual and auditory systems is integrated so as to reduce the variance in localization. (2) The effects of a remapping in the relation between visual and auditory space can be predicted from a simple learning rule. (3) The temporal propagation of errors in estimating the hand's state is captured by a linear dynamic observer, providing evidence for the existence of an intern...