Projektlogo

EML4U: Erkl?rbares Maschinelles Lernen für interaktive episodische Updates von Modellen

Overview

The goal of the project is to develop methods of ML explainability for a question that is highly relevant for practice: Which explanations can be offered to the user to make episodic interactive learning efficient and valid, especially in applications where manual data annotation is costly? In addition to a classical feature representation of data, the project will also consider latent representations in embedding spaces (as is common in automatic language processing and knowledge graph processing) that are relevant for practice.

Funding program: Erkl?rbarkeit und Transparenz des Maschinellen Lernens und der Künstlichen Intelligenz

Funding program

BMBF, Grant No. 001IS19080B

Key Facts

Grant Number:
001IS19080B
Project duration:
04/2020 - 03/2022
Funded by:
BMBF
Websites:
Homepage
Projektseite DICE
GITHUB
Recent Research Projects

More Information

Principal Investigators

contact-box image

Dr. Stefan Heindorf

Data Science Junior Research Group

About the person
contact-box image

Prof. Dr. Axel-Cyrille Ngonga Ngomo

Data Science / Heinz Nixdorf Institute

About the person

Project Team

contact-box image

Adrian Wilke, M.Sc.

Data Science / Heinz Nixdorf Institute

About the person

Cooperating Institutions

Universit?t Bielefeld

Cooperating Institution

Semalytix

Cooperating Institution

Go to website