What is not where: the challenge of integrating spatial representations into deep learning architectures.

John D. Kelleher Simon Dobnik

Published in: CoRR (2018)

Keyphrases

deep learning
unsupervised feature learning
deep belief networks
unsupervised learning
machine learning
spatial information
restricted boltzmann machine
mental models
multiscale
higher order
decision making
image representation
weakly supervised
question answering
supervised learning
pairwise
computer vision