Skip to main content

Deeply Explainable Intelligent Machines

Project description

Making robots explain their actions

In the EU-funded DEXIM project, the goal is to build a fully transparent end-to-end trainable and explainable deep learning approach for visual scene understanding. To achieve this goal, we will make use of the positive interactions between multiple data modalities, incorporate uncertainty and temporal continuity constraints, as well as memory mechanisms. The output of this proposal will have direct consequences for many practical applications, most notably in mobile robotics and intelligent vehicles industry. This project will therefore strengthen the user’s trust in a very competitive market.

Host institution

EBERHARD KARLS UNIVERSITAET TUEBINGEN
Net EU contribution
€ 1 500 000,00
Address
Geschwister-scholl-platz
72074 Tuebingen
Germany

See on map

Region
Baden-Württemberg Tübingen Tübingen, Landkreis
Activity type
Higher or Secondary Education Establishments
Non-EU contribution
€ 0,00

Beneficiaries (1)

EBERHARD KARLS UNIVERSITAET TUEBINGEN
Germany
Net EU contribution
€ 1 500 000,00
Address
Geschwister-scholl-platz
72074 Tuebingen

See on map

Region
Baden-Württemberg Tübingen Tübingen, Landkreis
Activity type
Higher or Secondary Education Establishments
Non-EU contribution
€ 0,00