A computational learning theory of active object recognition under uncertainty

DOI10.1007/s11263-012-0551-6zbMath1259.68192OpenAlexW2059501997MaRDI QIDQ1943411

Alexander Andreopoulos, John K. Tsotsos

Publication date: 20 March 2013

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11263-012-0551-6

zbMATH Keywords

attentionactive visionobject recognitionvisual searchcomputational complexity of vision

Mathematics Subject Classification ID

Computational learning theory (68Q32) Analysis of algorithms and problem complexity (68Q25) Pattern recognition, speech recognition (68T10) Machine vision and scene understanding (68T45)

Related Items (1)

A computational learning theory of active object recognition under uncertainty

Cites Work

• Unnamed Item
• Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
• Description and recognition of curved objects
• Localization vs. identification of semi-algebraic sets
• PAC-Bayesian stochastic model selection
• Fat-shattering and the learnability of real-valued functions
• A computational learning theory of active object recognition under uncertainty
• Deductive learning
• A theory of the learnable
• Contour Enhancement, Short Term Memory, and Constancies in Reverberating Neural Networks
• Spiking Neuron Models
• 10.1162/153244303321897690
• Efficient noise-tolerant learning from statistical queries
• Active object recognition: Looking for differences

This page was built for publication: A computational learning theory of active object recognition under uncertainty