{"id":2,"date":"2023-09-13T21:22:26","date_gmt":"2023-09-13T21:22:26","guid":{"rendered":"http:\/\/mortenmorup.dk\/?page_id=2"},"modified":"2023-09-24T19:36:24","modified_gmt":"2023-09-24T19:36:24","slug":"sample-page","status":"publish","type":"page","link":"https:\/\/mortenmorup.dk\/?page_id=2","title":{"rendered":"Software"},"content":{"rendered":"\n

Principal Convex Hull \/ Archetypal Analysis
<\/strong>Efficient algorithms for Archetypal Analysis for regular data, kernels and sparse data as described in\u00a0M. M\u00f8rup and L. K. Hansen, Archetypal Analysis for Data Mining,\u00a0Neural Computing 2011.
(<\/em>download .zip file<\/a>).<\/p>\n\n\n\n

Matlab scripts\u00a0(written by J. C. Th\u00f8gersen.)\u00a0accompanying the paper by\u00a0J. C. Th\u00f8gersen, M. M\u00f8rup, S. Damki\u00e6r, S. Molin and L. Jelsbak,\u00a0Archetypal analysis of diverse\u00a0Pseudomonas aeruginosa\u00a0transcriptomes reveals adaptation\u00a0in cystic fibrosis airways, BMC Bioinformatics, 2013.
(download .zip file<\/a>)\u00a0\u00a0\u00a0<\/p>\n\n\n\n


ERPWAVELAB<\/strong>
Software tool for analyzing event related EEG and MEG data. Among many functionalities, the toolbox include wavelet transformation, non-negative matrix and tensor factorization as well as various visualization methods\u00a0 (go to\u00a0www.erpwavelab.org<\/a>\u00a0to learn more).<\/p>\n\n\n\n


Exercise Material for CP and Tucker Decompositions
<\/strong>This exercise material is used for the teaching of tensor decomposition approaches for CP and Tucker decomposition as described in the review paper M. M\u00f8rup\u00a0Applications of tensor (multiway array) factorizations and decompositions in data mining,\u00a0Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery.<\/em>
(download .zip file<\/a>).<\/p>\n\n\n\n

ShiftCP
<\/strong>The shiftCP model as described in M. M\u00f8rup et al. \u201cShift Invariant Multilinear Decomposition of Neuroimaging Data\u201d NeuroImage 2008. The model is a generalization of the Canonical Decomposition\/PARAFAC (CP)model to include temporal shifts that are specific to a given mode of the tensor.
(download .zip file<\/a>)<\/p>\n\n\n\n


ConvCP
<\/strong>The Convolutive CP model is a generalization of the Canonical Decomposition\/PARAFAC (CP) model to include latency and shape changes. The model includes an implementation of automatic relevance determination in order to determine model order. The method is described in M. M\u00f8rup, K. H. Madsen, L. K. Hansen \u201cModeling trial based neuromaging data\u201d,\u00a0<\/em>NIPS 2008 workshop on\u00a0New Directions in Statistical Learning for Meaningful and Reproducible fMRI Analysis<\/em><\/a>\u00a0and\u00a0M. M\u00f8rup, L.K. Hansen, K. H. Madsen \u201cModeling Latency and Shape Changes in Trial Based Neuroimaging Data\u201d,\u00a0ASILOMAR-SSC 2011<\/em>.
(download .zip file<\/a>)<\/p>\n\n\n\n

Automatic Relevance Determination for CP and Tucker
<\/strong>This demo implements automatic relevance determination for the CP and Tucker models as described in our article M. M\u00f8rup and L. K. Hansen \u201cAutomatic Relevance Determination for Multiway Models\u201d,\u00a0Journal of Chemometrics.\u00a0<\/em>The code infers the number of components of the CP and Tucker model at the computational cost of fitting one ordinary model.\u00a0(download .zip file<\/a>)<\/p>\n\n\n\n

Bayesian Community Detection
<\/strong>This software implement our extension of the IRM model to enforce community structure in complex networks as described in our article entitled M. M\u00f8rup and M. N. Schmidt \u201cBayesian Community Detection\u201d\u00a0submitted to Neural Computation<\/em>.
(download .zip file<\/a>).<\/p>\n\n\n\n

Exercise material on the Infinite Relational Model
<\/strong>This exercise material include Matlab implementation of the IRM model for uni-partite and bi-partite networks including split-merge sampling and extensions to multi-graphs. Included are scripts for evaluating extracted structure by normalized mutual information and link-prediction.(download .zip file<\/a>).<\/p>\n\n\n\n

NLARS<\/strong>
This demo implements the non-negative least angle regression and selection method described in M.\u00a0M\u00f8rup, K. H. Madsen, L. K. Hansen \u201dApproximate L0 constrained Non-negative Matrix and Tensor Factorization\u201d\u00a0IEEE International Symposium on Circuits and Systems 2008<\/em>.
(download .zip file<\/a>)<\/p>\n","protected":false},"excerpt":{"rendered":"

Principal Convex Hull \/ Archetypal AnalysisEfficient algorithms for Archetypal Analysis for regular data, kernels and sparse data as described in\u00a0M. M\u00f8rup and L. K. Hansen, Archetypal Analysis for Data Mining,\u00a0Neural Computing 2011.(download .zip file). Matlab scripts\u00a0(written by J. C. Th\u00f8gersen.)\u00a0accompanying the paper by\u00a0J. C. Th\u00f8gersen, M. M\u00f8rup, S. Damki\u00e6r, S. Molin and L. Jelsbak,\u00a0Archetypal analysis […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"open","template":"","meta":{"footnotes":""},"_links":{"self":[{"href":"https:\/\/mortenmorup.dk\/index.php?rest_route=\/wp\/v2\/pages\/2"}],"collection":[{"href":"https:\/\/mortenmorup.dk\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mortenmorup.dk\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mortenmorup.dk\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/mortenmorup.dk\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2"}],"version-history":[{"count":4,"href":"https:\/\/mortenmorup.dk\/index.php?rest_route=\/wp\/v2\/pages\/2\/revisions"}],"predecessor-version":[{"id":76,"href":"https:\/\/mortenmorup.dk\/index.php?rest_route=\/wp\/v2\/pages\/2\/revisions\/76"}],"wp:attachment":[{"href":"https:\/\/mortenmorup.dk\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}