Invariant template matching in systems with spatiotemporal coding: a matter of instability

DOI10.1016/J.NEUNET.2009.01.014zbMATH Open1335.68219DBLPjournals/nn/TyukinTL09arXivcs/0702082OpenAlexW1978282545WikidataQ48715436 ScholiaQ48715436MaRDI QIDQ280336FDOQ280336

Tatiana A. Tyukina, C. van Leeuwen, I. Tyukin

Publication date: 10 May 2016

Published in: Neural Networks (Search for Journal in Brave)

Abstract: We consider the design of a pattern recognition that matches templates to images, both of which are spatially sampled and encoded as temporal sequences. The image is subject to a combination of various perturbations. These include ones that can be modeled as parameterized uncertainties such as image blur, luminance, translation, and rotation as well as unmodeled ones. Biological and neural systems require that these perturbations be processed through a minimal number of channels by simple adaptation mechanisms. We found that the most suitable mathematical framework to meet this requirement is that of weakly attracting sets. This framework provides us with a normative and unifying solution to the pattern recognition problem. We analyze the consequences of its explicit implementation in neural systems. Several properties inherent to the systems designed in accordance with our normative mathematical argument coincide with known empirical facts. This is illustrated in mental rotation, visual search and blur/intensity adaptation. We demonstrate how our results can be applied to a range of practical problems in template matching and pattern recognition.

Full work available at URL: https://arxiv.org/abs/cs/0702082

zbMATH Keywords

adaptationconvergenceLyapunov-unstablenonlinear parameterizationtemplate matchingweakly attracting sets

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10) Neural networks for/in biological studies, artificial life and related topics (92B20)

Cites Work

• Title not available (Why is that?)
• Nonlinear systems.
• Neural networks and physical systems with emergent collective computational abilities.
• Speed-gradient scheme and its application in adaptive control problems
• Chaotic itinerancy
• On the concept of attractor
• Pattern recognition and associative memory as dynamical processes in a synergetic system. I: Translation invariance, selective attention, and decomposition of scenes
• Hebbian learning reconsidered: Representation of static and dynamic objects in associative neural nets
• Spatial sampling design based on stochastic complexity.
• Group actions, homeomorphisms, and matching: A general framework
• Invariant template matching in systems with spatiotemporal coding: a matter of instability
• Lyapunov-like conditions of forward invariance and boundedness for a class of unstable systems
• Nonuniform Small-Gain Theorems for Systems with Unstable Invariant Sets
• Singularities of Transition Processes in Dynamical Systems: Qualitative Theory of Critical Delays
• Passivity Based Design of Synchronizing Systems
• Adaptation and Parameter Estimation in Systems With Unstable Target Dynamics and Nonlinear Parametrization

Cited In (3)

• Invariant template matching in systems with spatiotemporal coding: a matter of instability
• Free energy, value, and attractors
• Mixed \(H_\infty\) and passive exponential synchronization for singular Markov jump neural networks based on hybrid event trigger scheme

Recommendations

• Title not available (Why is that?) 👍 👎
• Invariance deformations and pattern recognition 👍 👎
• Invariant encoding of spatial stimulus topology in the temporal domain 👍 👎
• Matching of observations of dynamical systems, with applications to sequence matching 👍 👎
• Invariant object recognition in the visual system with error correction and temporal difference learning 👍 👎
• The trace model for spatial invariance with applications in structured pattern recognition, image patch matching and incremental visual tracking 👍 👎
• A unifying framework for invariant pattern recognition 👍 👎
• Template-based stabilization of relative equilibria in systems with continuous symmetry 👍 👎

This page was built for publication: Invariant template matching in systems with spatiotemporal coding: a matter of instability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q280336)