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

Online disturbance prediction for enhanced availability in smart grids

Kaitovic, Igor ; Malek, Miroslaw (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2017 ; 2017INFO011.

A gradual move in the electric power industry towards Smart Grids brings new challenges to the system's efficiency and dependability. With a growing complexity and massive introduction of renewable generation, particularly at the distribution level, the number of faults and, consequently, disturbances (errors and failures) is expected to increase significantly. This threatens to compromise...

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

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

Mining unstructured software data

Bacchelli, Alberto ; Lanza, Michele (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2013 ; 2013INFO003.

Our thesis is that the analysis of unstructured data supports software understanding and evolution analysis, and complements the data mined from structured sources. To this aim, we implemented the necessary toolset and investigated methods for exploring, exposing, and exploiting unstructured data.To validate our thesis, we focused on development email data. We found two main challenges in...

Università della Svizzera italiana

Teaching networks how to learn : reinforcement learning for data dissemination in wireless sensor networks

Förster, Anna ; Murphy, Amy L. (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2009 ; 2009INFO001.

Wireless sensor networks (WSNs) are a fast developing research area with many new exciting applications arising, ranging from micro climate and environmental monitoring through health and structural monitoring to interplanetary communications. At the same time researchers have invested a lot of time and effort into developing high performance energy efficient and reliable communication protocols...

Università della Svizzera italiana

Adaptive routing in ad hoc wireless multi-hop networks

Ducatelle, Frederick ; Gambardella, Luca Maria (Dir.)

Thèse de doctorat : Università della Svizzera italiana, 2007 ; 2007INFO001.

Ad hoc wireless multi-hop networks (AHWMNs) are communication networks that consist entirely of wireless nodes, placed together in an ad hoc manner, i.e. with minimal prior planning. All nodes have routing capabilities, and forward data packets for other nodes in multi-hop fashion. Nodes can enter or leave the network at any time, and may be mobile, so that the network topology continuously...