BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:From spatial learning to machine learning: an unsupervised approac
 h with applications to behavioral science - Mihaela Pricop-jeckstadt (Tech
 nische Universität Dresden)
DTSTART:20171103T120000Z
DTEND:20171103T125000Z
UID:TALK94429@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:In this talk we consider an example-driven approach for identi
 fying ability patterns from data partitions based on learning behaviour in
  the water maze experiment. A modification of the k-means algorithm for lo
 ngitudinal data as introduced in [1] is used to identify clusters based on
  the learning variable (see [3]). The association between these clusters a
 nd the flying ability variables is statistically tested in order to charac
 terize the partitions in terms of flying traits. Since the learning variab
 les seem to reflect flying abilities\, we propose a new sparse clustering 
 algorithm in an approach modelling the covariance matrix by a  Kronecker p
 roduct. Consistency and an EM-algorithm are studied in this framework also
 .  References: 1. Genolini\, C.\; Ecochard\, R.\; Benghezal\, M. et al.\,&
 nbsp\;&#39\;&#39\;kmlShape: An Efficient Method to Cluster Longitudinal Da
 ta (Time-Series) According to Their Shapes&#39\;&#39\;\, PLOS ONE\; Vol. 1
 1\, 2016.2.  Sung\, K.K. and Poggio\, T.\, &#39\;&#39\;Example-based learn
 ing for view-based human face detection&#39\;&#39\;\; IEEE Transactions on
  pattern analysis and machine intelligence\, Vol. 20\, 39-51\, 1998.\; 3. 
 Rosipal\, R. and Kraemer\, N. \, &#39\;&#39\;Overview and recent advances 
 in partial least squares&#39\;&#39\;\,&nbsp\; Subspace\, latent structure 
 and feature selection\,&nbsp\; Book Series: Lecture Notes in Computer Scie
 nce\; Vol. 3940\, 34-51\, 2006.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR