Abstract Recurrent neural networks are powerful models used for sequence learning. This thesis addresses the typical limitation of recurrent neural networks to fully process and update for every timestep of an input sequence, even if the...

Abstract This thesis aims to improve usability in 3D selection tasks by using wearable haptic technology. We explore (i) the use of proximity-based cues and embodiment illusions, (ii) combinations of pseudo-haptics with...

Prof. Dr. Michael Rose, CML principal investigator in project B3, has acquired a new DFG-funded project titled "Relevance of neuronal pre-stimulus oscillatory activity for the formation of crossmodal episodic memory”, starting in 2021 and...

Colloquium by Priv.Doz. Dr. Patrick Bruns

Wednesday, 20 January 2021 16:15, Zoom Meeting
Please contact the organizers for Zoom Meeting ID and password.

Colloquium by Prof. Dr. Esfandiar Mohammadi, University of Lübeck

Thursday, 14 January 2021 17:15, Zoom Meeting

Abstract: Neural networks are used to tackle a wide variety of non-trivial problems if they are fed a massive amount of...

Colloquium by Prof. Dr. Ulrike von Luxburg

Thursday, 14 January 2021 14:00, Zoom Meeting
Zoom Meeting ID: https://uni-hamburg.zoom.us/j/92033612558?pwd=TVFRV1FmOC9SczA2cWlGRUtFYXVWUT09

AI Predicts Asymptomatic Carriers of COVID-19 published in Nature Scientific Reports

A group of researchers including Prof. Dr. Jianwei Zhang, CML speaker and principal investigator in project A4, B5, Z1 and Z3, has published a...

Colloquium by Timo Gerkmann, University of Hamburg

Thursday, 10 December 2020, 16:00, Zoom Meeting
Please see the ZMNH bAIome seminar for zoom access information.

Colloquium by John Danaher

Thursday, 03 December 2020, 18:15, Zoom Meeting
Register here to get access to the lecture:
https://www.inf.uni-hamburg.de/en/inst/ab/eit/taming-the-machines/winter20-21.html

John Danaher is a Senior...

Colloquium by Prof. Dr. Justus Piater, Leopold-Franzens-Universität Innsbruck

Thursday, 19 November 2020, 16:00, Zoom Meeting
Zoom Meeting ID: 868 5039 6499, passwd: 851315