|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM252590600 |
| 003 |
DE-627 |
| 005 |
20231224164432.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231224s2015 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2015.2392947
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n0842.xml
|
| 035 |
|
|
|a (DE-627)NLM252590600
|
| 035 |
|
|
|a (NLM)26353184
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Orchard, Garrick
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a HFirst
|b A Temporal Approach to Object Recognition
|
| 264 |
|
1 |
|c 2015
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 27.05.2016
|
| 500 |
|
|
|a Date Revised 10.12.2019
|
| 500 |
|
|
|a published: Print
|
| 500 |
|
|
|a Citation Status MEDLINE
|
| 520 |
|
|
|a This paper introduces a spiking hierarchical model for object recognition which utilizes the precise timing information inherently present in the output of biologically inspired asynchronous address event representation (AER) vision sensors. The asynchronous nature of these systems frees computation and communication from the rigid predetermined timing enforced by system clocks in conventional systems. Freedom from rigid timing constraints opens the possibility of using true timing to our advantage in computation. We show not only how timing can be used in object recognition, but also how it can in fact simplify computation. Specifically, we rely on a simple temporal-winner-take-all rather than more computationally intensive synchronous operations typically used in biologically inspired neural networks for object recognition. This approach to visual computation represents a major paradigm shift from conventional clocked systems and can find application in other sensory modalities and computational tasks. We showcase effectiveness of the approach by achieving the highest reported accuracy to date (97.5% ± 3.5%) for a previously published four class card pip recognition task and an accuracy of 84.9% ± 1.9% for a new more difficult 36 class character recognition task
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, Non-U.S. Gov't
|
| 700 |
1 |
|
|a Meyer, Cedric
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Etienne-Cummings, Ralph
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Posch, Christoph
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Thakor, Nitish
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Benosman, Ryad
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 37(2015), 10 vom: 01. Okt., Seite 2028-40
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:37
|g year:2015
|g number:10
|g day:01
|g month:10
|g pages:2028-40
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2015.2392947
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 37
|j 2015
|e 10
|b 01
|c 10
|h 2028-40
|