论文信息 - Local Feature Extraction - What Receptive Field Size Should Be Used?

Local Feature Extraction - What Receptive Field Size Should Be Used?

Biologically inspired hierarchical networks for image processing are based on parallel feature extraction across the image using feature detectors that have a limited Receptive Field (RF). It is, h ...

Chandan Roy | Mohammad Saifullah | Rita Kovordányi

[1] R. O’Reilly,et al. Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain , 2000 .

[2] R. Kovordányi,et al. IMPROVED GENERALIZATION IN A RECURRENT HIERARCHICAL NETWORK USING A MIXTURE OF ERROR-DRIVEN AND HEBBIAN LEARNING , 2009 .

[3] Kunihiko Fukushima,et al. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[4] David G. Lowe,et al. University of British Columbia. , 1945, Canadian Medical Association journal.

[5] Chandan Roy,et al. Cyclone track forecasting based on satellite images using artificial neural networks , 2009 .

[6] Randall C. O'Reilly,et al. Generalization in Interactive Networks: The Benefits of Inhibitory Competition and Hebbian Learning , 2001, Neural Computation.

[7] Thomas Serre,et al. Robust Object Recognition with Cortex-Like Mechanisms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8] T. Poggio,et al. Hierarchical models of object recognition in cortex September 23 , 1999 , 1999 .

[9] Brian Mingus,et al. The Emergent neural modeling system , 2008, Neural Networks.

[10] Thomas Serre,et al. Object recognition with features inspired by visual cortex , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).