Invariant template matching in systems with spatiotemporal coding: a matter of instability
From MaRDI portal
Publication:280336
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.
Recommendations
- Invariant encoding of spatial stimulus topology in the temporal domain
- A unifying framework for invariant pattern recognition
- Invariant object recognition in the visual system with error correction and temporal difference learning
- Invariance deformations and pattern recognition
- The trace model for spatial invariance with applications in structured pattern recognition, image patch matching and incremental visual tracking
- scientific article; zbMATH DE number 1980919
- Template-based stabilization of relative equilibria in systems with continuous symmetry
- Matching of observations of dynamical systems, with applications to sequence matching
Cites work
- scientific article; zbMATH DE number 3891160 (Why is no real title available?)
- Adaptation and Parameter Estimation in Systems With Unstable Target Dynamics and Nonlinear Parametrization
- Chaotic itinerancy
- Group actions, homeomorphisms, and matching: A general framework
- Hebbian learning reconsidered: Representation of static and dynamic objects in associative neural nets
- 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
- Neural networks and physical systems with emergent collective computational abilities
- Nonlinear systems.
- Nonuniform Small-Gain Theorems for Systems with Unstable Invariant Sets
- On the concept of attractor
- Passivity Based Design of Synchronizing Systems
- Pattern recognition and associative memory as dynamical processes in a synergetic system. I: Translation invariance, selective attention, and decomposition of scenes
- Singularities of Transition Processes in Dynamical Systems: Qualitative Theory of Critical Delays
- Spatial sampling design based on stochastic complexity.
- Speed-gradient scheme and its application in adaptive control problems
Cited in
(4)- Invariant template matching in systems with spatiotemporal coding: a matter of instability
- Free energy, value, and attractors
- Invariant encoding of spatial stimulus topology in the temporal domain
- Mixed \(H_\infty\) and passive exponential synchronization for singular Markov jump neural networks based on hybrid event trigger scheme
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)
