Learning Semantic Prediction using Pretrained Deep Feedforward Networks

Jörg Wagner, Volker Fischer, Michael Herman, Sven Behnke

European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2017, Bruges, Belgium, April 26 – 28, 2017

Abstract:

The ability to predict future environment states is crucial for anticipative behavior of autonomous agents. Deep learning based methods have proven to solve key perception challenges but currently mainly operate in a non-predictive fashion. We bridge this gap by proposing an approach to transform trained feed-forward networks into predictive ones via a combination of a recurrent predictive module with a teacher-student training strategy. This transformation can be conducted without the need of labeled data in a fully self-supervised fashion. Using simulated data, we demonstrate the ability of the resulting model to temporally predict a task-specific representation and additionally show the benefits of using our approach even when no corresponding feed-forward model is available.

PDF Bibtex

@INPROCEEDINGS{Wagner2017ESANN,
  author={Jörg Wagner and Volker Fischer and Michael Herman and Sven Behnke},
  booktitle={25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)},
  title={Learning Semantic Prediction using Pretrained Deep Feedforward Networks},
  year={2017},
  month={April},
}