Cargando…
The DIAMOND Model: Deep Recurrent Neural Networks for Self-Organizing Robot Control
The proposed architecture applies the principle of predictive coding and deep learning in a brain-inspired approach to robotic sensorimotor control. It is composed of many layers each of which is a recurrent network. The component networks can be spontaneously active due to the homeokinetic learning...
Autores principales: | Smith, Simón C., Dharmadi, Richard, Imrie, Calum, Si, Bailu, Herrmann, J. Michael |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7523181/ https://www.ncbi.nlm.nih.gov/pubmed/33041778 http://dx.doi.org/10.3389/fnbot.2020.00062 |
Ejemplares similares
-
SORN: A Self-Organizing Recurrent Neural Network
por: Lazar, Andreea, et al.
Publicado: (2009) -
RM-SORN: a reward-modulated self-organizing recurrent neural network
por: Aswolinskiy, Witali, et al.
Publicado: (2015) -
Robot Communication: Network Traffic Classification Based on Deep Neural Network
por: Ge, Mengmeng, et al.
Publicado: (2021) -
Transformation-invariant visual representations in self-organizing spiking neural networks
por: Evans, Benjamin D., et al.
Publicado: (2012) -
Dynamical Integration of Language and Behavior in a Recurrent Neural Network for Human–Robot Interaction
por: Yamada, Tatsuro, et al.
Publicado: (2016)