Show simple item record

dc.contributor.authorLotter, William Edward
dc.contributor.authorKreiman, Gabriel
dc.contributor.authorCox, David Daniel
dc.date.accessioned2017-10-13T21:16:54Z
dc.date.issued2016
dc.identifier.citationLotter, William, Gabriel Kreiman, and David Cox. 2016. "Deep predictive coding networks for video prediction and unsupervised learning." Working paoer.en_US
dc.identifier.urihttp://nrs.harvard.edu/urn-3:HUL.InstRepos:34216388
dc.description.abstractWhile great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning - leveraging unlabeled examples to learn about the structure of a domain - remains a difficult unsolved challenge. Here, we explore prediction of future frames in a video sequence as an unsupervised learning rule for learning about the structure of the visual world. We describe a predictive neural network ("PredNet") architecture that is inspired by the concept of "predictive coding" from the neuroscience literature. These networks learn to predict future frames in a video sequence, with each layer in the network making local predictions and only forwarding deviations from those predictions to subsequent network layers. We show that these networks are able to robustly learn to predict the movement of synthetic (rendered) objects, and that in doing so, the networks learn internal representations that are useful for decoding latent object parameters (e.g. pose) that support object recognition with fewer training views. We also show that these networks can scale to complex natural image streams (car-mounted camera videos), capturing key aspects of both egocentric movement and the movement of objects in the visual scene, and the representation learned in this setting is useful for estimating the steering angle. Altogether, these results suggest that prediction represents a powerful framework for unsupervised learning, allowing for implicit learning of object and scene structure.en_US
dc.description.sponsorshipEngineering and Applied Sciencesen_US
dc.language.isoen_USen_US
dc.relation.hasversionhttps://arxiv.org/abs/1605.08104en_US
dash.licenseLAA
dc.titleDeep Predictive Coding Networks for Video Prediction and Unsupervised Learningen_US
dc.typeResearch Paper or Reporten_US
dc.description.versionAuthor's Originalen_US
dash.depositing.authorCox, David Daniel
dc.date.available2017-10-13T21:16:54Z
workflow.legacycommentsFAR2016en_US
dash.contributor.affiliatedLotter, William
dash.contributor.affiliatedKreiman, Gabriel
dash.contributor.affiliatedCox, David


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record