Connectionists: PhD and Postdoc positions KU Leuven: Optimization frameworks for deep kernel machines

[Johan Suykens]

PhD and Postdoc positions KU Leuven: Optimization frameworks for deep 
kernel machines

The research group KU Leuven ESAT-STADIUS is currently offering 2 PhD 
and 1 Postdoc (1 year, extendable) positions within the framework of the 
KU Leuven C1 project Optimization frameworks for deep kernel machines 
(promotors: Prof. Johan Suykens and Prof. Panos Patrinos).

Deep learning and kernel-based learning are among the very powerful 
methods in machine learning and data-driven modelling. From an 
optimization and model representation point of view, training of deep 
feedforward neural networks occurs in a primal form, while kernel-based 
learning is often characterized by dual representations, in connection 
to possibly infinite dimensional problems in the primal. In this project 
we aim at investigating new optimization frameworks for deep kernel 
machines, with feature maps and kernels taken at multiple levels, and 
with possibly different objectives for the levels. The research 
hypothesis is that such an extended framework, including both deep 
feedforward networks and deep kernel machines, can lead to new important 
insights and improved results. In order to achieve this, we will study 
optimization modelling aspects (e.g. variational principles, distributed 
learning formulations, consensus algorithms), accelerated learning 
schemes and adversarial learning methods.

The PhD and Postdoc positions in this KU Leuven C1 project (promotors: 
Prof. Johan Suykens and Prof. Panos Patrinos) relate to the following 
possible topics:

-1- Optimization modelling for deep kernel machines
-2- Efficient learning schemes for deep kernel machines
-3- Adversarial learning for deep kernel machines

For further information and on-line applying, see
https://www.kuleuven.be/personeel/jobsite/jobs/54740654" (PhD positions) and
https://www.kuleuven.be/personeel/jobsite/jobs/54740649" (Postdoc position)
(click EN for English version).

The research group ESAT-STADIUS http://www.esat.kuleuven.be/stadius at 
the university KU Leuven Belgium provides an excellent research 
environment being active in the broad area of mathematical engineering, 
including data-driven modelling, neural networks and machine learning, 
nonlinear systems and complex networks, optimization, systems and 
control, signal processing, bioinformatics and biomedicine.