A biologically motivated visual memory architecture for online learning of objects

Neural Networks : the Official Journal of the International Neural Network Society
Stephan KirsteinEdgar Körner

Abstract

We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that implements short-term and long-term memory for objects. A particular focus is the functional realization of online and incremental learning for the task of appearance-based object recognition of many complex-shaped objects. We propose some modifications of learning vector quantization algorithms that are especially adapted to the task of incremental learning and capable of dealing with the stability-plasticity dilemma of such learning algorithms. Our technical implementation of the neural architecture is capable of online learning of 50 objects within less than three hours.

References

Sep 20, 1991·Science·L R Squire, S Zola-Morgan
Apr 1, 1987·Psychological Review·Irving Biederman
Mar 1, 1996·Cerebral Cortex·G Buzsáki
Sep 15, 1998·Cognition·M J Tarr, H H Bülthoff
Sep 4, 1999·Behavioural Brain Research·I IzquierdoD M Barros
Oct 20, 1999·Nature Neuroscience·M Riesenhuber, T Poggio
Feb 7, 2001·Current Opinion in Neurobiology·Y Miyashita, T Hayashi
Jun 20, 2001·Neural Networks : the Official Journal of the International Neural Network Society·F H Hamker
Nov 3, 2001·Science·P Maquet
Apr 26, 2002·Neural Computation·Dan RothNarendra Ahuja
Dec 12, 2002·Trends in Cognitive Sciences·Randall C. O'Reilly, Kenneth A. Norman
Mar 29, 2003·Neural Networks : the Official Journal of the International Neural Network Society·E KörnerT Rodemann
Jun 21, 2003·Neural Computation·Heiko Wersing, Edgar Körner
Feb 1, 1957·Journal of Neurology, Neurosurgery, and Psychiatry·W B SCOVILLE, B MILNER
Mar 23, 2004·Nature Reviews. Neuroscience·Thomas J Palmeri, Isabel Gauthier
Sep 29, 2004·Proceedings of the National Academy of Sciences of the United States of America·Nicola J BroadbentRobert E Clark
Sep 13, 2005·Neural Networks : the Official Journal of the International Neural Network Society·Shen Furao, Osamu Hasegawa
Oct 11, 2005·Neural Computation·Sethu VijayakumarStefan Schaal
Aug 19, 2007·International Journal of Neural Systems·Heiko WersingEdgar Körner

❮ Previous
Next ❯

Citations

Dec 18, 2008·Biological cybernetics·Tim C KietzmannMartin Riedmiller
Jan 10, 2012·Neural Networks : the Official Journal of the International Neural Network Society·Stephan KirsteinEdgar Körner
Jun 16, 2011·Neural Computation·Mathias FranziusLaurenz Wiskott

❮ Previous
Next ❯

Related Concepts

Related Feeds

Cajal Bodies & Gems

Cajal bodies or coiled bodies are dense foci of coilin protein. Gemini of Cajal bodies, or gems, are microscopically similar to Cajal bodies. It is believed that Cajal bodies play important roles in RNA processing while gems assist the Cajal bodies. Find the latest research on Cajal bodies and gems here.

Related Papers

Neural Networks : the Official Journal of the International Neural Network Society
Seiichi OzawaNikola Kasabov
International Journal of Neural Systems
Heiko WersingEdgar Körner
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shivani AgarwalDan Roth
© 2021 Meta ULC. All rights reserved