Results 1  10
of
520
Information Theory and Statistics
, 1968
"... Entropy and relative entropy are proposed as features extracted from symbol sequences. Firstly, a proper Iterated Function System is driven by the sequence, producing a fractaMike representation (CSR) with a low computational cost. Then, two entropic measures are applied to the CSR histogram of th ..."
Abstract

Cited by 1161 (0 self)
 Add to MetaCart
Entropy and relative entropy are proposed as features extracted from symbol sequences. Firstly, a proper Iterated Function System is driven by the sequence, producing a fractaMike representation (CSR) with a low computational cost. Then, two entropic measures are applied to the CSR histogram of the CSR and theoretically justified. Examples are included.
The induction of dynamical recognizers
 Machine Learning
, 1991
"... A higher order recurrent neural network architecture learns to recognize and generate languages after being "trained " on categorized exemplars. Studying these networks from the perspective of dynamical systems yields two interesting discoveries: First, a longitudinal examination of the learning pro ..."
Abstract

Cited by 210 (14 self)
 Add to MetaCart
A higher order recurrent neural network architecture learns to recognize and generate languages after being "trained " on categorized exemplars. Studying these networks from the perspective of dynamical systems yields two interesting discoveries: First, a longitudinal examination of the learning process illustrates a new form of mechanical inference: Induction by phase transition. A small weight adjustment causes a "bifurcation" in the limit behavior of the network. This phase transition corresponds to the onset of the network’s capacity for generalizing to arbitrarylength strings. Second, a study of the automata resulting from the acquisition of previously published training sets indicates that while the architecture is not guaranteed to find a minimal finite automaton consistent with the given exemplars, which is an NPHard problem, the architecture does appear capable of generating nonregular languages by exploiting fractal and chaotic dynamics. I end the paper with a hypothesis relating linguistic generative capacity to the behavioral regimes of nonlinear dynamical systems.
A Survey of Shape Analysis Techniques
 Pattern Recognition
, 1998
"... This paper provides a review of shape analysis methods. Shape analysis methods play an important role in systems for object recognition, matching, registration, and analysis. Researchin shape analysis has been motivated, in part, by studies of human visual form perception systems. ..."
Abstract

Cited by 200 (2 self)
 Add to MetaCart
This paper provides a review of shape analysis methods. Shape analysis methods play an important role in systems for object recognition, matching, registration, and analysis. Researchin shape analysis has been motivated, in part, by studies of human visual form perception systems.
ReactionDiffusion Textures
 Computer Graphics
, 1991
"... We present a method for texture synthesisbased on the simulation of a process of local nonlinear interaction, called reactiondiffusion, which has been proposed as a model of biological pattern formation. We extend traditional reactiondiffusion systems by allowing anisotropic and spatially nonunif ..."
Abstract

Cited by 129 (0 self)
 Add to MetaCart
We present a method for texture synthesisbased on the simulation of a process of local nonlinear interaction, called reactiondiffusion, which has been proposed as a model of biological pattern formation. We extend traditional reactiondiffusion systems by allowing anisotropic and spatially nonuniform diffusion, as well as multiple competing directions of diffusion. We adapt reactiondiffusion systems to the needs of computer graphics by presenting a method to synthesize patterns which compensate for the effects of nonuniform surface parameterization. Finally, we develop efficient algorithms for simulating reactiondiffusion systems and display a collection of resulting textures using standard texture and displacementmapping techniques. 1 Introduction Texture mapping techniques have become so highly developed and so widely used that textureless images tend to appear barren, unrealistic, and boring. To date, though, techniques for synthesizing natural textures have advanced far less...
The Dynamical Hypothesis in Cognitive Science
 Behavioral and Brain Sciences
, 1997
"... The dynamical hypothesis is the claim that cognitive agents are dynamical systems. It stands opposed to the dominant computational hypothesis, the claim that cognitive agents are digital computers. This target article articulates the dynamical hypothesis and defends it as an open empirical alternati ..."
Abstract

Cited by 111 (1 self)
 Add to MetaCart
The dynamical hypothesis is the claim that cognitive agents are dynamical systems. It stands opposed to the dominant computational hypothesis, the claim that cognitive agents are digital computers. This target article articulates the dynamical hypothesis and defends it as an open empirical alternative to the computational hypothesis. Carrying out these objectives requires extensive clarification of the conceptual terrain, with particular focus on the relation of dynamical systems to computers. Key words cognition, systems, dynamical systems, computers, computational systems, computability, modeling, time. Long Abstract The heart of the dominant computational approach in cognitive science is the hypothesis that cognitive agents are digital computers; the heart of the alternative dynamical approach is the hypothesis that cognitive agents are dynamical systems. This target article attempts to articulate the dynamical hypothesis and to defend it as an empirical alternative to the compu...
Modeling and estimation of multiresolution stochastic processes
 IEEE TRANS. ON INFORMATION THEORY
, 1992
"... An overview is provided of the several components of a research effort aimed at the development of a theory of multiresolution stochastic modeling and associated techniques for optimal multiscale statistical signal and image processing. As described, a natural framework for developing such a theory ..."
Abstract

Cited by 94 (17 self)
 Add to MetaCart
An overview is provided of the several components of a research effort aimed at the development of a theory of multiresolution stochastic modeling and associated techniques for optimal multiscale statistical signal and image processing. As described, a natural framework for developing such a theory is the study of stochastic processes indexed by nodes on lattices or trees in which different depths in the tree or lattice correspond to different spatial scales in representing a signal or image. In particular, it will be seen how the wavelet transform directly suggests such a modeling paradigm. This perspective then leads directly to the investigation of several classes of dynamic models and related notions of “ multiscale stationarity ” in which scale plays the role of a timelike variable. Focus is primarily on the investigation of models on homogenous trees. In particular, the elements of a dynamic system theory on trees are described
Constructing Deterministic FiniteState Automata in Recurrent Neural Networks
 Journal of the ACM
, 1996
"... Recurrent neural networks that are trained to behave like deterministic finitestate automata (DFAs) can show deteriorating performance when tested on long strings. This deteriorating performance can be attributed to the instability of the internal representation of the learned DFA states. The use o ..."
Abstract

Cited by 70 (16 self)
 Add to MetaCart
Recurrent neural networks that are trained to behave like deterministic finitestate automata (DFAs) can show deteriorating performance when tested on long strings. This deteriorating performance can be attributed to the instability of the internal representation of the learned DFA states. The use of a sigmoidal discriminant function together with the recurrent structure contribute to this instability. We prove that a simple algorithm can construct secondorder recurrent neural networks with a sparse interconnection topology and sigmoidal discriminant function such that the internal DFA state representations are stable, i.e. the constructed network correctly classifies strings of arbitrary length. The algorithm is based on encoding strengths of weights directly into the neural network. We derive a relationship between the weight strength and the number of DFA states for robust string classification. For a DFA with n states and m input alphabet symbols, the constructive algorithm genera...
Dynamical systems, Measures and Fractals via Domain Theory
 Information and Computation
, 1995
"... We introduce domain theory in dynamical systems, iterated function systems (fractals) and measure theory. For a discrete dynamical system given by the action of a continuous map f:X X on a metric space X, we study the extended dynamical systems (l/X,l/f), (UX, U f) and (LX, Lf) where 1/, U and L ar ..."
Abstract

Cited by 68 (19 self)
 Add to MetaCart
We introduce domain theory in dynamical systems, iterated function systems (fractals) and measure theory. For a discrete dynamical system given by the action of a continuous map f:X X on a metric space X, we study the extended dynamical systems (l/X,l/f), (UX, U f) and (LX, Lf) where 1/, U and L are respectively the Vietoris hyperspace, the upper hyperspace and the lower hyperspace functors. We show that if (X, f) is chaotic, then so is (UX, U f). When X is locally compact UX, is a continuous bounded complete dcpo. If X is second countable as well, then UX will be omegacontinuous and can be given an effective structure. We show how strange attractors, attractors of iterated function systems (fractals) and Julia sets are obtained effectively as fixed points of deterministic functions on UX or fixed points of nondeterministic functions on CUX where C is the convex (Plotkin) power domain. We also show that the set, M(X), of finite Borel measures on X can be embedded in PUX, where P is the probabilistic power domain. This provides an effective framework for measure theory. We then prove that the invariant measure of an hyperbolic iterated function system with probabilities can be obtained as the unique fixed point of an associated continuous function on PUX.
Agentbased computational models and generative social science
 Complexity
, 1999
"... This article argues that the agentbased computational model permits a distinctive approach to social science for which the term “generative ” is suitable. In defending this terminology, features distinguishing the approach from both “inductive ” and “deductive ” science are given. Then, the followi ..."
Abstract

Cited by 64 (0 self)
 Add to MetaCart
This article argues that the agentbased computational model permits a distinctive approach to social science for which the term “generative ” is suitable. In defending this terminology, features distinguishing the approach from both “inductive ” and “deductive ” science are given. Then, the following specific contributions to social science are discussed: The agentbased computational model is a new tool for empirical research. It offers a natural environment for the study of connectionist phenomena in social science. Agentbased modeling provides a powerful way to address certain enduring—and especially interdisciplinary—questions. It allows one to subject certain core theories—such as neoclassical microeconomics—to important types of stress (e.g., the effect of evolving preferences). It permits one to study how rules of individual behavior give rise—or “map up”—to macroscopic regularities and organizations. In turn, one can employ laboratory behavioral research findings to select among competing agentbased (“bottom up”) models. The agentbased approach may well have the important effect of decoupling individual rationality from macroscopic equilibrium and of separating decision science from social science more generally. Agentbased modeling offers powerful new forms of hybrid theoreticalcomputational work; these are particularly relevant to the study of nonequilibrium systems. The agentbased approach invites the interpretation of society as a distributed computational device, and in turn the interpretation of social dynamics as a type of computation. This interpretation raises important foundational issues in social science—some related to intractability, and some to undecidability proper. Finally, since “emergence” figures prominently in this literature, I take up the connection between agentbased modeling and classical emergentism, criticizing the latter and arguing that the two are incompatible. � 1999 John Wiley &
Domain Theory and Integration
 Theoretical Computer Science
, 1995
"... We present a domaintheoretic framework for measure theory and integration of bounded realvalued functions with respect to bounded Borel measures on compact metric spaces. The set of normalised Borel measures of the metric space can be embedded into the maximal elements of the normalised probabilis ..."
Abstract

Cited by 57 (12 self)
 Add to MetaCart
We present a domaintheoretic framework for measure theory and integration of bounded realvalued functions with respect to bounded Borel measures on compact metric spaces. The set of normalised Borel measures of the metric space can be embedded into the maximal elements of the normalised probabilistic power domain of its upper space. Any bounded Borel measure on the compact metric space can then be obtained as the least upper bound of an !chain of linear combinations of point valuations (simple valuations) on the upper space, thus providing a constructive setup for these measures. We use this setting to define a new notion of integral of a bounded realvalued function with respect to a bounded Borel measure on a compact metric space. By using an !chain of simple valuations, whose lub is the given Borel measure, we can then obtain increasingly better approximations to the value of the integral, similar to the way the Riemann integral is obtained in calculus by using step functions. ...