Scene Context Classification with Event-Driven Spiking Deep Neural Networks

Event-Driven computation is attracting growing attention among researchers for several reasons. On one hand, the availability of new bio-inspired retina-like vision sensors that provide spiking outputs, like the Dynamic Vision Sensor (DVS) make it possible to demonstrate energy efficient and high-sp...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Negri, P.
Otros Autores: Soto, M., Linares-Barranco, B., Serrano-Gotarredona, T.
Formato: Acta de conferencia Capítulo de libro
Lenguaje:Inglés
Publicado: Institute of Electrical and Electronics Engineers Inc. 2019
Acceso en línea:Registro en Scopus
DOI
Handle
Registro en la Biblioteca Digital
Aporte de:Registro referencial: Solicitar el recurso aquí
LEADER 06174caa a22006497a 4500
001 PAPER-25755
003 AR-BaUEN
005 20230518205752.0
008 190410s2019 xx ||||fo|||| 10| 0 eng|d
024 7 |2 scopus  |a 2-s2.0-85062300105 
040 |a Scopus  |b spa  |c AR-BaUEN  |d AR-BaUEN 
100 1 |a Negri, P. 
245 1 0 |a Scene Context Classification with Event-Driven Spiking Deep Neural Networks 
260 |b Institute of Electrical and Electronics Engineers Inc.  |c 2019 
506 |2 openaire  |e Política editorial 
504 |a Szummer, M., Picard, R.W., Indoor-outdoor image classification (1998) International Workshop on Content-Based Access of Image and Video Database, pp. 42-51. , Jan 
504 |a Lichtsteiner, P., Posch, C., Delbruck, T., A 128128 120db 15us latency asynchronous temporal contrast vision sensor (2008) JSSC, 43 (2), pp. 566-576 
504 |a Posch, C., Matolin, D., Wohlgenannt, R., A qvga 143 db dynamic range frame-free PWM image sensor with lossless pixel-level video compression and time-domain cds (2011) IEEE J. of Solid-State Circ, 46 (1), pp. 259-275. , Jan 
504 |a Serrano-Gotarredona, T., Linares-Barranco, B., A 128x128 1. 5sensitivity 0. 9sensor using transimpedance preamplifiers (2013) IEEE Journal of Solid-State Circuits, 48 (3), pp. 827-838 
504 |a Guo, M., Huang, J., Chen, S., Live demonstration: A 768-640 pixels 200meps dynamic vision sensor (2017) 2017 IEEE International Symposium on Circuits and Systems (ISCAS), p. 1. , May 
504 |a Son, B., Suh, Y., Kim, S., Jung, H., Kim, J.S., Shin, C., Park, K., Ryu, H., 4. 1 a 640x480 dynamic vision sensor with a 9um pixel and 300meps address-event representation (2017) 2017 IEEE International Solid-State Circuits Conference (ISSCC), pp. 66-67. , Feb 
504 |a Pérez-Carrasco, J., Mapping from frame-driven to frame-free event-driven vision systems by low-rate rate coding and coincidence processing-application to feedforward convnets (2013) PAMI, 35 (11), pp. 2706-2719 
504 |a Lungu, I.A., Corradi, F., Delbrck, T., Live demonstration: Convolutional neural network driven by dynamic vision sensor playing roshambo (2017) 2017 IEEE International Symposium on Circuits and Systems (ISCAS), , May 
504 |a (2018) MegaSim, , https://bitbucket.org/bernabelinares/megasim 
504 |a Sivilotti, M., (1991) Wiring Considerations in Analog VLSI Systems with Application to Field-programmable Networks, , PhD, Computation and Neural Systems, Caltech, Pasadena California 
504 |a Stromatias, E., Soto, M., Serrano-Gotarredona, T., Linares-Barranco, B., An event-driven classifier for spiking neural networks fed with synthetic or dynamic vision sensor data (2017) Frontiers in Neuroscience, 11, p. 350 
504 |a Bottou, L., Large-scale machine learning with stochastic gradient descent (2010) International Conference on Computational Statistics, pp. 177-187. , Physica-Verlag HD 
520 3 |a Event-Driven computation is attracting growing attention among researchers for several reasons. On one hand, the availability of new bio-inspired retina-like vision sensors that provide spiking outputs, like the Dynamic Vision Sensor (DVS) make it possible to demonstrate energy efficient and high-speed complex vision tasks. On the other hand, the emergence of abundant new nanoscale devices that operate as tunable two-terminal resistive elements, which when operated through dynamic pulsing techniques emulate learning and processing in the brain, promise an explosion of highly compact energy efficient neuromorphic event-driven applications. In this paper we focus for the first time on a high-level cognitive task, namely scene context classification, performed by event-driven computations and using real sensory data from a DVS camera. © 2018 IEEE.  |l eng 
536 |a Detalles de la financiación: TEC2015-63884-C2-1-P 
536 |a Detalles de la financiación: European Regional Development Fund 
536 |a Detalles de la financiación: H2020 Euratom, EURATOM, 644096 
536 |a Detalles de la financiación: 687299, NEURAM3 
536 |a Detalles de la financiación: ACKNOWLEDGMENTS This work was funded by EU H2020 grants 644096 (ECO-MODE) and 687299 (NEURAM3), and by Spanish grant from the Ministry of Economy and Competitivity TEC2015-63884-C2-1-P (COGNET) (with support from the European Regional Development Fund). 
593 |a Instituto en Ciencias de la Computación (UBA-CONICET), Buenos Aires, Argentina 
593 |a Instituto de Microelectrónica de Sevilla (IMSE-CNM), CSIC, Universidad de Sevilla, Sevilla, Spain 
690 1 0 |a ENERGY EFFICIENCY 
690 1 0 |a CONTEXT CLASSIFICATION 
690 1 0 |a DYNAMIC VISION SENSORS 
690 1 0 |a ENERGY EFFICIENT 
690 1 0 |a EVENT DRIVEN APPLICATIONS 
690 1 0 |a NANOSCALE DEVICE 
690 1 0 |a PULSING TECHNIQUE 
690 1 0 |a RESISTIVE ELEMENTS 
690 1 0 |a VISION SENSORS 
690 1 0 |a DEEP NEURAL NETWORKS 
700 1 |a Soto, M. 
700 1 |a Linares-Barranco, B. 
700 1 |a Serrano-Gotarredona, T. 
711 2 |d 9 December 2018 through 12 December 2018  |g Código de la conferencia: 144481 
773 0 |d Institute of Electrical and Electronics Engineers Inc., 2019  |h pp. 569-572  |p IEEE Int. Conf. Electron. Circuits Syst., ICECS  |n 2018 25th IEEE International Conference on Electronics Circuits and Systems, ICECS 2018  |z 9781538695623  |t 25th IEEE International Conference on Electronics Circuits and Systems, ICECS 2018 
856 4 1 |u https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062300105&doi=10.1109%2fICECS.2018.8617982&partnerID=40&md5=a8602571eca19b18cf99e8988043c47d  |y Registro en Scopus 
856 4 0 |u https://doi.org/10.1109/ICECS.2018.8617982  |y DOI 
856 4 0 |u https://hdl.handle.net/20.500.12110/paper_97815386_v_n_p569_Negri  |y Handle 
856 4 0 |u https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97815386_v_n_p569_Negri  |y Registro en la Biblioteca Digital 
961 |a paper_97815386_v_n_p569_Negri  |b paper  |c PE 
962 |a info:eu-repo/semantics/conferenceObject  |a info:ar-repo/semantics/documento de conferencia  |b info:eu-repo/semantics/publishedVersion 
999 |c 86708