Hide metadata

dc.contributor.authorGorton, Patrick Ribu
dc.date.accessioned2020-08-21T23:52:31Z
dc.date.available2020-08-21T23:52:31Z
dc.date.issued2020
dc.identifier.citationGorton, Patrick Ribu. Backpropagating to the Future. Master thesis, University of Oslo, 2020
dc.identifier.urihttp://hdl.handle.net/10852/78816
dc.description.abstractPredicting the future using deep learning is a research field of increasing interest. The majority of contributions concern architectural designs for predictive models, however, there is a lack of established evaluation methods for assessing their predictive abilities. Images and videos are targeted towards human observers, and since humans have individual perceptions of the world, evaluation of videos should take subjectivity into account. With the absence of appropriate evaluation methods, measuring the performance of predictive models and comparing different model architectures is challenging. In this thesis, I present a protocol for evaluating predictive models using subjective data. The evaluation method is applied in an experiment to measure the realism and accuracy of predictions of a visual traffic environment. These predictions are generated by a proposed model architecture, which produces discrete latent representations of the environment. Application of the evaluation method reveals that the proposed deep learning model proves to be capable of producing accurate predictions ten seconds into the environment’s future. The predictive model is also shown to be robust in terms of processing different image types for describing the environment. The proposed evaluation method is shown to be uncorrelated with the predominant approach for evaluating predictive models, which is a frame-wise comparison between predictions and ground truth. These findings emphasise the importance of using subjective data in the assessment of predictive abilities of models, and open up a new alternative of evaluating predictive deep learning models.eng
dc.language.isoeng
dc.subjectCrowdsourcing
dc.subjectVideo
dc.subjectPredictive Modelling
dc.subjectMixed Methods Design
dc.subjectPredicting the Future
dc.subjectVideo Prediction
dc.subjectDeep Learning
dc.subjectModel Evaluation
dc.titleBackpropagating to the Futureeng
dc.typeMaster thesis
dc.typeGroup thesis
dc.date.updated2020-08-22T23:46:25Z
dc.creator.authorGorton, Patrick Ribu
dc.identifier.urnURN:NBN:no-81812
dc.type.documentMasteroppgave
dc.type.documentGruppeoppgave
dc.identifier.fulltextFulltext https://www.duo.uio.no/bitstream/handle/10852/78816/1/patriri_master_thesis.pdf


Files in this item

Appears in the following Collection

Hide metadata