Expectation Learning for Adaptive Crossmodal Stimuli Association

EUCog Meeting Proceedings - Nov 2017. Open Access
Associated documents : BarrosEUCog2017.pdf [296Ko]  
The human brain is able to learn, generalize, and predict crossmodal stimuli. Learning by expectation fine-tunes crossmodal processing at different levels, thus enhancing our power of generalization and adaptation in highly dynamic environments. In this paper, we propose a deep neural architecture trained by using expectation learning accounting for unsupervised learning tasks. Our learning model exhibits a self-adaptable behavior, setting the first steps towards the development of deep learning architectures for crossmodal stimuli association.

 

@InProceedings\{BPFLW17,
  author       = "Barros, Pablo and Parisi, German I. and Fu, Di and Liu, Xun and Wermter, Stefan",
  title        = "Expectation Learning for Adaptive Crossmodal Stimuli Association",
  booktitle    = "EUCog Meeting Proceedings",
  month        = "Nov",
  year         = "2017",
  publisher    = "EUCog Meeting",
  organization = "EUCog",
  url          = "https://www2.informatik.uni-hamburg.de/wtm/publications/2017/BPFLW17/"
}

» Pablo Barros
» German I. Parisi
» Di Fu
» Xun Liu
» Stefan Wermter