Machine Learning and Deep Learning

One of the main research topics of the L3S in the field of artificial intelligence is Machine Learning and Deep Learning.

Conditional Coding for Learned Image and Video Compression

This project deals with learning-based video coding using a meta-learning-based procedure for regularization and dynamic adaptation of the decoder.

Green AutoML for Driver Assistance Systems

The aim of the GreenAutoML4FAS project is to design a holistic, carbon-efficient system for driver assistance systems

GLACIATION

GLACIATION aims to reduce carbon emissions by developing a distributed knowledge graph that improves the efficiency of big data analysis.

ixAutoML

Making automatic machine learning systems more human-centered by enabling interactivity and explainability.

Leibniz AI Academy

Development and establishment of a transcurricular, cross-disciplinary micro-degree program "Leibniz AI Academy" at Leibniz Universität Hannover (LUH).

MoToRes

Route recommendations for individual user needs, regional specifics and optimal utilisation of transport and attractions.

Online Optimierung

The goal of the project is to develop and investigate online convex optimization (OCO)-based control schemes for general cost functions and constraints without relying on restrictive assumptions.

PlanOS

The PlanOs project aims to develop large-area sensor networks in thin polymer films for strain and shape measurement with high efficiency, low cost and high resolution.

ROMEO

The ROMEO project aims to improve multimodal (kinesthetic and tactile) information integration for robot-mediated remote manipulation.

Robotics Lab

The L3S’s Robot Learning Lab works on foundational research to develop increasingly autonomous assistive systems.

SWIFTT will provide forest managers with affordable, simple and effective remote sensing tools backed up by powerful machine learning models. It will offer a holistic health monitoring service to detect and map various risks for forests and their managers

Towards a Framework for Assessing Explanation Quality (TRR 318 INF)

In this project, we study the pragmatic goal of all explaining processes: to be successful — that is, for the explanation to achieve the intended form of understanding.