Abstract:
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.
Registro:
Documento: |
Conferencia
|
Título: | Scene Context Classification with Event-Driven Spiking Deep Neural Networks |
Autor: | Negri, P.; Soto, M.; Linares-Barranco, B.; Serrano-Gotarredona, T. |
Filiación: | Instituto en Ciencias de la Computación (UBA-CONICET), Buenos Aires, Argentina Instituto de Microelectrónica de Sevilla (IMSE-CNM), CSIC, Universidad de Sevilla, Sevilla, Spain
|
Palabras clave: | Energy efficiency; Context classification; Dynamic vision sensors; Energy efficient; Event driven applications; Nanoscale device; Pulsing technique; Resistive elements; Vision sensors; Deep neural networks |
Año: | 2019
|
Página de inicio: | 569
|
Página de fin: | 572
|
DOI: |
http://dx.doi.org/10.1109/ICECS.2018.8617982 |
Título revista: | 25th IEEE International Conference on Electronics Circuits and Systems, ICECS 2018
|
Título revista abreviado: | IEEE Int. Conf. Electron. Circuits Syst., ICECS
|
Registro: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97815386_v_n_p569_Negri |
Referencias:
- 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
- Lichtsteiner, P., Posch, C., Delbruck, T., A 128128 120db 15us latency asynchronous temporal contrast vision sensor (2008) JSSC, 43 (2), pp. 566-576
- 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
- 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
- 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
- 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
- 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
- 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
- (2018) MegaSim, , https://bitbucket.org/bernabelinares/megasim
- Sivilotti, M., (1991) Wiring Considerations in Analog VLSI Systems with Application to Field-programmable Networks, , PhD, Computation and Neural Systems, Caltech, Pasadena California
- 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
- Bottou, L., Large-scale machine learning with stochastic gradient descent (2010) International Conference on Computational Statistics, pp. 177-187. , Physica-Verlag HD
Citas:
---------- APA ----------
Negri, P., Soto, M., Linares-Barranco, B. & Serrano-Gotarredona, T.
(2019)
. Scene Context Classification with Event-Driven Spiking Deep Neural Networks. 25th IEEE International Conference on Electronics Circuits and Systems, ICECS 2018, 569-572.
http://dx.doi.org/10.1109/ICECS.2018.8617982---------- CHICAGO ----------
Negri, P., Soto, M., Linares-Barranco, B., Serrano-Gotarredona, T.
"Scene Context Classification with Event-Driven Spiking Deep Neural Networks"
. 25th IEEE International Conference on Electronics Circuits and Systems, ICECS 2018
(2019) : 569-572.
http://dx.doi.org/10.1109/ICECS.2018.8617982---------- MLA ----------
Negri, P., Soto, M., Linares-Barranco, B., Serrano-Gotarredona, T.
"Scene Context Classification with Event-Driven Spiking Deep Neural Networks"
. 25th IEEE International Conference on Electronics Circuits and Systems, ICECS 2018, 2019, pp. 569-572.
http://dx.doi.org/10.1109/ICECS.2018.8617982---------- VANCOUVER ----------
Negri, P., Soto, M., Linares-Barranco, B., Serrano-Gotarredona, T. Scene Context Classification with Event-Driven Spiking Deep Neural Networks. IEEE Int. Conf. Electron. Circuits Syst., ICECS. 2019:569-572.
http://dx.doi.org/10.1109/ICECS.2018.8617982