XLIII Jornadas De Automática: Libro De Actas: 7, 8 Y 9 De Septiembre De 2022, Logroño (La Rioja) 2022
DOI: 10.17979/spudc.9788497498418.0216
|View full text |Cite
|
Sign up to set email alerts
|

Entrenamiento supervisado de redes neuronales de impulsos

Abstract: En este trabajo se explora una nueva estrategia de entrenamiento supervisado con Redes Neuronales de Impulsos (Spiking Neural Network, SNN) para forecasting en series temporales. En la actualidad, la inmensa mayoría de los trabajos en SNN se centran principalmente en problemas de clasificación, muy especialmente de imágenes. En este sentido, el trabajo aquí presentado es uno de los primeros trabajos en aplicar SNN para forecasting de series temporales, siendo los resultados muy prometedores. Para validar la me… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 11 publications
0
1
0
Order By: Relevance
“…The increasing number of adoptions by the community is symbolic of the success of a framework. Since being open-sourced in December 2019, SpikingJelly has been widely used in many spiking deep learning studies, including adversarial attack (100, 101), ANN2SNN (95,(102)(103)(104)(105)(106), attention mechanisms (107,108), depth estimation from DVS data (69,109), development of innovative materials (110), emotion recognition (111), energy estimation (112), eventbased video reconstruction (113), fault diagnosis (114), hardware design (115)(116)(117), network structure improvements (60,61,(118)(119)(120)(121), spiking neuron improvements (56,(122)(123)(124)(125)(126)(127), training method improvements (128)(129)(130)(131)(132)(133)(134)(135)(136)(137)(138), medical diagnosis (139,140), network pruning …”
Section: Adoptions By the Communitymentioning
confidence: 99%
“…The increasing number of adoptions by the community is symbolic of the success of a framework. Since being open-sourced in December 2019, SpikingJelly has been widely used in many spiking deep learning studies, including adversarial attack (100, 101), ANN2SNN (95,(102)(103)(104)(105)(106), attention mechanisms (107,108), depth estimation from DVS data (69,109), development of innovative materials (110), emotion recognition (111), energy estimation (112), eventbased video reconstruction (113), fault diagnosis (114), hardware design (115)(116)(117), network structure improvements (60,61,(118)(119)(120)(121), spiking neuron improvements (56,(122)(123)(124)(125)(126)(127), training method improvements (128)(129)(130)(131)(132)(133)(134)(135)(136)(137)(138), medical diagnosis (139,140), network pruning …”
Section: Adoptions By the Communitymentioning
confidence: 99%