Title :
Learning and recognition of similar temporal sequences
Author :
Fujii, Robert H. ; Hayashi, Taiichiro
Author_Institution :
Univ. of Aizu, Aizu Wakamatsu, Japan
Abstract :
Learning and recognition of object velocity sequences using a hierarchical network similar in structure to the mammalian neocortex is proposed. Space and time invariant representations of velocity sequences are captured in an unsupervised manner. Recognition of similar sequences are achieved by allowing some variance in the learned velocity vectors.
Keywords :
image motion analysis; medical image processing; object recognition; unsupervised learning; hierarchical network similar; mammalian neocortex; object recognition; similar temporal sequences; space invariant representations; time invariant representations; velocity sequences; Animal structures; Cities and towns; Feedforward neural networks; Neural networks; Neurofeedback; Object recognition; Output feedback; Proposals; Shape; Unsupervised learning;
Conference_Titel :
Circuits and Systems, 2009. MWSCAS '09. 52nd IEEE International Midwest Symposium on
Conference_Location :
Cancun
Print_ISBN :
978-1-4244-4479-3
Electronic_ISBN :
1548-3746
DOI :
10.1109/MWSCAS.2009.5235908
