Università della Svizzera italiana

New architectures for very deep learning

Srivastava, Rupesh Kumar ; Schmidhuber, Jürgen (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2018 ; 2018INFO006.

Artificial Neural Networks are increasingly being used in complex real- world applications because many-layered (i.e., deep) architectures can now be trained on large quantities of data. However, training even deeper, and therefore more powerful networks, has hit a barrier due to fundamental limitations in the design of existing networks. This thesis develops new architectures that, for the...

Università della Svizzera italiana

Advances in humanoid control and perception

Stollenga, Marijn Frederik ; Schmidhuber, Jürgen (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2016 ; 2016INFO004.

One day there will be humanoid robots among us doing our boring, time-consuming, or dangerous tasks. They might cook a delicious meal for us or do the groceries. For this to become reality, many advances need to be made to the artificial intelligence of humanoid robots. The ever-increasing available computational processing power opens new doors for such advances. In this thesis we develop...

Università della Svizzera italiana

Towards adaptive and autonomous humanoid robots : from vision to actions

Leitner, Jürgen ; Schmidhuber, Jürgen (Dir.) ; Förster, Alexander (Codir.)

Thèse de doctorat : Università della Svizzera italiana, 2014 ; 2014INFO020.

Although robotics research has seen advances over the last decades robots are still not in widespread use outside industrial applications. Yet a range of proposed scenarios have robots working together, helping and coexisting with humans in daily life. In all these a clear need to deal with a more unstructured, changing environment arises. I herein present a system that aims to overcome the...

Università della Svizzera italiana

Slowness learning for curiosity-driven agents

Kompella, Varun Raj ; Schmidhuber, Jürgen (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2014 ; 2014INFO013.

In the absence of external guidance, how can a robot learn to map the many raw pixels of high-dimensional visual inputs to useful action sequences? I study methods that achieve this by making robots self-motivated (curious) to continually build compact representations of sensory inputs that encode different aspects of the changing environment. Previous curiosity-based agents acquired skills by...

Università della Svizzera italiana

Learning to reach and reaching to learn : a unified approach to path planning and reactive control through reinforcement learning

Frank, Mikhail Alexander ; Schmidhuber, Jürgen (Dir.) ; Förster, Alexander (Codir.)

Thèse de doctorat : Università della Svizzera italiana, 2014 ; 2014INFO011.

The next generation of intelligent robots will need to be able to plan reaches. Not just ballistic point to point reaches, but reaches around things such as the edge of a table, a nearby human, or any other known object in the robot’s workspace. Planning reaches may seem easy to us humans, because we do it so intuitively, but it has proven to be a challenging problem, which continues to...

Università della Svizzera italiana

Advances in deep learning for vision, with applications to industrial inspection : classification, segmentation and morphological extensions

Masci, Jonathan ; Schmidhuber, Jürgen (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2014 ; 2014INFO001.

Learning features for object detection and recognition with deep learning has received increasing attention in the past several years and recently attained widespread popularity. In this PhD thesis we investigate its applications to the automatic surface inspection system of our industrial partner ArcelorMittal, for classification and segmentation problems. Currently employed algorithms, in...

Università della Svizzera italiana

Algorithms and complexity results for discrete probabilistic reasoning tasks

Mauá, Denis Deratani ; Schmidhuber, Jürgen (Dir.) ; Zaffalon, Marco (Codir.) ; Polpo de Campos, Cassio (Codir.)

Thèse de doctorat : Università della Svizzera italiana, 2013 ; 2013INFO005.

Many solutions to problems in machine learning and artificial intelligence involve solving a combinatorial optimization problem over discrete variables whose functional dependence is conveniently represented by a graph. This thesis addresses three types of these combinatorial optimization problems, namely, the maximum a posteriori inference in discrete probabilistic graphical models, the...

Università della Svizzera italiana

On the generation of representations for reinforcement learning

Sun, Yi ; Schmidhuber, Jürgen (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2012 ; 2012INFO001.

Creating autonomous agents that learn to act from sequential interactions has long been perceived as one of the ultimate goals of Artificial Intelligence (AI). Reinforcement Learning (RL), a subfield of Machine Learning (ML), addresses important aspects of this objective. This dissertation investigates a particular problem encountered in RL called representation generation. Two related...

Università della Svizzera italiana

Online Dynamic Algorithm Portfolios : minimizing the computational cost of problem solving

Gagliolo, Matteo ; Schmidhuber, Jürgen (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2010 ; 2010INFO004.

This thesis presents methods for minimizing the computational effort of problem solving. Rather than looking at a particular algorithm, we consider the issue of computational complexity at a higher level, and propose techniques that, given a set of candidate algorithms, of unknown performance, learn to use these algorithms while solving a sequence of problem instances, with the aim of...