Show simple item record

dc.contributor.authorNikoo, Hassan
dc.date.accessioned2015-08-17T17:07:29Z
dc.date.available2015-08-17T17:07:29Z
dc.identifier.urihttp://hdl.handle.net/10222/60293
dc.description.abstractDetection of spatiotemporal patterns have many applications in areas such as computer vision and data mining. Specifically, the analysis and mining of biological data with high dimensionality (e.g. multi-cell recordings, fMRI) are heavily dependent on detection of these patterns. In this thesis, we propose two unsupervised learning algorithms for obtaining filters that capture temporal patterns. In particular, we are interested in applying our methods for detection of regularities in multi-cell recordings of neurons. We propose two approaches: convolutional restricted Boltzmann machine (RBM) and convolutional denoising auto-encoder. The experimental results demonstrate that the proposed methods are able to detect temporal patterns in artificial data and multi-cell recordings from rat's brain. Moreover, we propose a Monte Carlo method for quantitatively evaluating the convolutional RBM by estimating the log-likelihood of data under the model distribution. The experimental results on test dataset of handwritten digits (MNIST), demonstrate that the convolutional RBM can learn a good generative model with small number of parameters.en_US
dc.language.isoen_USen_US
dc.subjectConvolutional denoising auto-encoderen_US
dc.subjectUnsupervised representation learningen_US
dc.subjectconvolutional restricted Boltzmann machineen_US
dc.subjectMulti-cell recordingen_US
dc.subjectrat auditory cortexen_US
dc.subjectAnealed Importance Samplingen_US
dc.subjectmachine learningen_US
dc.titleSpatiotemporal Pattern Detection in Multi-cell Recordings Using Unsupervised Learningen_US
dc.typeThesisen_US
dc.date.defence2015-07-23
dc.contributor.departmentFaculty of Computer Scienceen_US
dc.contributor.degreeMaster of Computer Scienceen_US
dc.contributor.external-examinerN/Aen_US
dc.contributor.graduate-coordinatorEvangelos Miliosen_US
dc.contributor.thesis-readerDirk Arnolden_US
dc.contributor.thesis-readerSageev Ooreen_US
dc.contributor.thesis-supervisorThomas Trappenbergen_US
dc.contributor.ethics-approvalNot Applicableen_US
dc.contributor.manuscriptsNot Applicableen_US
dc.contributor.copyright-releaseNot Applicableen_US
 Find Full text

Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record