Title :
Temporal binding, segmentation and attention focusing in the olfactory model
Author :
Lysetskiy, Mykola ; Zurada, Jacek M.
Author_Institution :
Dept. of Electr. & Comput. Eng., Louisville Univ., KY, USA
Abstract :
A biologically inspired model of the olfactory cortex is proposed which realizes mapping of the input pattern temporal structure to the spatial dynamic of the ensemble of output integrate-and-fire neurons. The temporal-to-spatial mapping and distributed representation of the model allows realization of both rough cluster classification and fine recognition of patterns within a cluster in parallel and as parts of the same dynamic process. The temporal structure of the system provides the base for the modeling of multi-pattern processing. The model is able to extract components of complex odor patterns (which are the spatio-temporal sequences of neural activity), segment and bind them temporally
Keywords :
chemioception; neural nets; pattern classification; physiological models; attention focusing; biologically inspired model; complex odor patterns; distributed representation; fine recognition; input pattern temporal structure; multi-pattern processing; neural activity; olfactory cortex; olfactory model; output integrate-and-fire neurons; rough cluster classification; segmentation; spatial dynamic; spatio-temporal sequences; temporal binding; temporal structure; temporal-to-spatial mapping; Biological information theory; Biological system modeling; Biological systems; Brain modeling; Encoding; Information processing; Neurons; Object recognition; Olfactory; Pattern recognition;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.939513
