Λέσχη Φίλων Στατιστικής - GrStats forum
Deep Learning AUEB Seminar - Wed 14 Oct 2015: Representation and deep learning with Bayesian non-parametric models Forumgrstats

Join the forum, it's quick and easy

Λέσχη Φίλων Στατιστικής - GrStats forum
Deep Learning AUEB Seminar - Wed 14 Oct 2015: Representation and deep learning with Bayesian non-parametric models Forumgrstats
Λέσχη Φίλων Στατιστικής - GrStats forum
Would you like to react to this message? Create an account in a few clicks or log in to continue.
Για προβλήματα εγγραφής και άλλες πληροφορίες επικοινωνήστε με : grstats.forum@gmail.com ή grstats@stat-athens.aueb.gr

Go down
grstats
grstats
Posts : 934
Join date : 2009-10-21
http://stat-athens.aueb.gr/~grstats/

Deep Learning AUEB Seminar - Wed 14 Oct 2015: Representation and deep learning with Bayesian non-parametric models Empty Deep Learning AUEB Seminar - Wed 14 Oct 2015: Representation and deep learning with Bayesian non-parametric models

Mon 12 Oct 2015 - 14:33
Ανακοίνωση σεμιναρίου:

Τετάρτη *14 Οκτωβρίου, ώρα 15:00 στην αίθουσα 607* (στο κτήριο της Ευελπίδων)
θα δοθεί ομιλία από τον Ανδρέα Δαμιανού o οποίος εργάζεται ως ερευνητής
στο Πανεπιστήμιο του Sheffield. Πληροφορίες για το θέμα του
σεμιναρίου και τον ομιλητή δίνονται παρακάτω.

Μιχάλης

-------------------------------- --------------------------------------
Title: Representation and deep learning with Bayesian non-parametric models

Abstract:
The high-dimensional and complex nature of real world data makes them difficult to visualise, understand, predict and, in general, work with. Similarly, consolidating multiple distinct but related data sources, for example coming from related biological experiments, is a non-trivial task. This talk will present a family of Bayesian probabilistic models which attempt to solve the aforementioned problems by encapsulating the notion of a latent space, i.e. an assumed "simpler" but unknown representation of the data which we seek to infer probabilistically. By additionally including extra prior knowledge or assumptions we obtain a plethora of model variants, such as timeseries and deep models. All these models are seen as special cases of the main framework which is called a "deep Gaussian process". My talk will also contain illustrative application examples from the domains of humanoid robotics, vision and bioinformatics.

Keywords: Gaussian processes, deep learning, humanoid robotics, Bayesian non-parametrics, timeseries analysis, multi-view data

Andreas Damianou
http://staffwww.dcs.sheffield.ac.uk/people/A.Damianou/research/index.html
Research associate,
University of Sheffield,
Dept. of Computer Science,
Sheffield Center for Robotics
and Sheffield Institute for Translational Neuroscience.

Back to top
Permissions in this forum:
You cannot reply to topics in this forum