on the regions corresponding to the ques-tion, because different questions inquire about the attributes of different image regions. We introduce an attention based configurable convolutional neural network (ABC-CNN) to learn such question-guided attention. ABC-CNN deter-mines an attention map for an image

In online handwriting recognition the trajectory of the pen is recorded during writing. Although the trajectory provides a compact and complete representation of the written output, it is hard to transcribe directly, because each letter is spread over many pen locations. Most recognition systems

Work supported by the European Union 7th Framework Program under the

Hiermit versichere ich, dass ich die vorliegende Doktorarbeit selbstständig verfasst und keine anderen als die angegebenen Hilfsmittel verwendet habe. Alle Textauszüge und Grafiken, die sinngemäß oder wörtlich aus veröffentlichten Schriften entnommen wurden, sind durch Ref-erenzen gekennzeichnet.

This work presents two different trans-lation models using recurrent neural net-works. The first one is a word-based ap-proach using word alignments. Second, we present phrase-based translation mod-els that are more consistent with phrase-based decoding. Moreover, we introduce bidirectional

recurrent networks to be trained directly for sequence labelling tasks where the align-ment between the inputs and the labels is unknown, and (2) an extension of long short-term memory to multidimensional data, such as images and video sequences. Experimental results are presented on speech recognition

Abstract not found

Published by the University of Miami ISBN 978-0-615-54865-4 Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice

2. Univ.-Prof. Dr.-Ing. W. Hemmert Die Dissertation wurde am 24.04.2014 bei der Technischen Universität München einge-reicht und durch die Fakultät für Elektrotechnik und Informationstechnik am 20.10.2014 angenommen. Acknowledgment This thesis would not have been possible without the support of many people. First of all, I would like to thank my supervisor Prof. Gerhard Rigoll for giving me the opportunity to work at the Institute for Human-Machine Communication at TUM and for the advices and support he gave me during my time at the institute. Fur-thermore, I would like to thank Prof. Werner Hemmert for doing the second review of this thesis. Over the years, fruitful discussions with colleagues contributed to the success of my work. Here I would like to mention Dr. Martin Hofmann, Prof. Björn

complies with the regulations of the University and meets the accepted standards with respect to originality and quality. Signed by the final examining committee: