Biologically Plausible Neural Learning using Symmetric Predictive Estimators

dc.contributor.authorXu, David
dc.date.accessioned2016-08-04T16:01:04Z
dc.date.available2016-08-04T16:01:04Z
dc.date.issued2016-08-04
dc.date.submitted2016-07-21
dc.description.abstractA predictive estimator (PE) is a neural microcircuit hypothesized to explain how the brain processes certain types of information. They participate in a hierarchy, passing predictions to lower layers, which send back prediction errors. Meanwhile, the network learns optimal connection weights in order to minimize the prediction errors. This two-way process has been used to hypothesize models for brain mechanisms, such as visual information processing. However, the standard implementation for a PE uses the same weight matrix for both feed-forward and feed-back projections, which is not biologically plausible. In this thesis, we investigate the predictive estimator using individual feed-forward and feed-back connection weights. We extend the model and introduce the Symmetric Predictive Estimator (SPE). We investigate the dynamics of a SPE network, analyze its stability, and define a general learning rule. A functional model of the SPE is implemented analytically, and in a neural framework using spiking neurons. Both implementations are built as Python modules that can accept generic, numerical inputs. With a series of general experiments, we demonstrate its ability to learn non-linear functions and perform a supervised-learning task. This variation on the PE may provide insights to the theory of predictive estimators and their role in the brain.en
dc.identifier.urihttp://hdl.handle.net/10012/10612
dc.language.isoenen
dc.pendingfalse
dc.publisherUniversity of Waterlooen
dc.subjectpredictive codingen
dc.subjectneural networksen
dc.subjectcomputational neuroscienceen
dc.subjectpredictive estimatorsen
dc.subjectbiological plausibilityen
dc.subjectperceptual networken
dc.titleBiologically Plausible Neural Learning using Symmetric Predictive Estimatorsen
dc.typeMaster Thesisen
uws-etd.degreeMaster of Mathematicsen
uws-etd.degree.departmentDavid R. Cheriton School of Computer Scienceen
uws-etd.degree.disciplineComputer Scienceen
uws-etd.degree.grantorUniversity of Waterlooen
uws.contributor.advisorOrchard, Jeff
uws.contributor.affiliation1Faculty of Mathematicsen
uws.peerReviewStatusUnrevieweden
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws.scholarLevelGraduateen
uws.typeOfResourceTexten

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Xu_David.pdf
Size:
4.05 MB
Format:
Adobe Portable Document Format
Description:
Thesis

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
6.17 KB
Format:
Item-specific license agreed upon to submission
Description: