Lecture2Go Videokatalog F.6 - Mathematik, Informatik, Naturwissenschaften Informatik Informatisches Kolloquium

Videokatalog

Lizenz: UHH-L2G

2027 Aufrufe

07.05.2018

Informatik

What is Embodiment, and How Does It Affect the Way We Function?

The slides shown during the Talk are available as a PDF under the download tab.

The way humans learn is very much affected by the fact that we have an embodiment - a physical location in the world, and the ability to change the world (both through physical interaction and through spoken and written communication with other agents). Ideas about the effect of human embodiment can be used to improve the functionality and learning strategies of artificial embodied systems, such as autonomous cars, humanoid robots, exoskeletons, search and rescue robots, etc.. I like to think about the effect of embodiment on our learning in three related ways:

1. We are able to alter the state of the scene we are observing so as to learn aspects of it that are not apparent from a first look. For example, we can move our head to look from a different angle, or squeeze, push or shake an object to investigate it.

2. Humans have a very limited communication bandwidth compared to the internal computation capacity in the brain. This means that we cannot easily perform reasoning together with other humans in the way a computer cluster can share computations. It also means that communication between humans is heavily under-determined and error-prone.

3. This limited bandwidth also means that we are forced to learn from quite few examples, and are extremely good at transfer learning and abstraction of knowledge. For example, it has been shown that a child can learn to recognize an unseen animal, e.g., elephants from a single simple drawing. This indicates that humans use very different visual learning strategies than state of the art Computer Vision systems.
This has implications for how to design artificial embodied systems, especially systems that should collaborate with, learn from, and solve problems together with humans.
In the context of this, I will outline a few of the projects in my group.

Teilen
Herunterladen
Technischer Support

Herunterladen

Video

Audio

Folien

Dieses Video darf in andere Webseiten eingebunden werden. Kopieren Sie dazu den Code zum Einbetten und fügen Sie diesen an der gewünschten Stelle in den HTML-Text einer Webseite ein. Geben Sie dabei bitte immer die Quelle an und verweisen Sie auf Lecture2Go!

Zitat2Go

Start Definiert den Startpunkt für Zitat2Go. Bitte in das Feld klicken, um die aktuelle Zeit auszuwählen.
Ende Definiert den Endpunkt für Zitat2Go. Bitte in das Feld klicken, um die aktuelle Zeit auszuwählen.
Zitat2Go-Link Nach der Auswahl eines Start- und Endpunktes verweist dieser Link auf den Ausschnitt des Videos.
IFrame Code Nutzen Sie diesen Code, um den Auschnitt des Videos mit dem Lecture2Go-Videoplayer einzubetten.

Technischer Support

Bitte klicken Sie auf den nachfolgenden Link und füllen Sie daraufhin die notwendigen Felder aus, um unser Support-Team zu kontaktieren! Link zu der RRZ-Support-Seite

Serie

24.01.2022

Scalable and Fast Cloud Data Management

Dr. Felix Gessert, Dr. Wolfram Wingerath, Prof. Dr. Norbert Ritter
25.01.2021

Informatikkolloquium WS20/21 - Matthias Rarey

Prof. Dr. Matthias Rarey
11.01.2021

Informatikkolloquium - 11.01.2021 Gregor Kasieczka

Jun. Prof. Dr. Gregor Kasieczka
15.06.2020

From Quantum Dynamics to Quantum Networks

Prof. Dr. Peter Schmelcher
17.02.2020

Ubiquitous Health: Wearable Computing Systems that Increase Quality of Life and Transform Health Care

Prof Bjoern Eskofier
13.01.2020

Privacy and/or Trust?

Dr Jörg Daubert
09.12.2019

Künstliche Intelligenz zwischen Science und Fiction

Prof. Dr. Prof. h.c. Andreas Dengel
02.12.2019

Technological development and application of Deep Learning in Biomedicine

Dr. Stefan Bonn
18.11.2019

Blind multi-microphone noise reduction and dereverberation algorithms for speech communication applications

Prof. Dr. Simon Doclo
20.05.2019

Deep Machines That Know When They Do not Know

Prof. Dr. Kristian Kersting
06.05.2019

Opportunistic Networks - Challenges and Opportunities

Prof. Dr. Anna Förster
15.04.2019

Known Operator Learning? A new Paradigm for Machine Learning in Signal Processing & Physics

Prof. Dr.-Ing. habil. Andreas Maier
01.04.2019

Empirical Studies into Modelling in Software Development in the Age of Big Data and AI

Prof. Dr. Michel Chaudron
28.01.2019

The innovations, industry problems, and research challenges open source has given us

Prof. Dr. Dirk Riehle
10.12.2018

Exploring Server-side Blocking of Regions

PhD Sadia Afroz
26.11.2018

Microarchitectural Attacks on modern CPUs

Prof. Dr. Thomas Eisenbarth
22.10.2018

Language dynamics in social media

Prof. Dr. Animesh Mukherjee
09.07.2018

Imitation learning, zero-shot learning and automated fact checking

Prof. Dr. Andreas Vlachos
25.06.2018

An Integrative, Event-Predictive Perspective on Cognition: Behavioral Evidence and Artificial Neural Network Models

Prof. Dr. Martin V. Butz
18.06.2018

Wem gehören die Daten? Zugangs- und Verfügungsmodelle in der Datenökonomie

Prof. Dr. phil. Ingrid Schneider
07.05.2018

What is Embodiment, and How Does It Affect the Way We Function?

Prof. Hedvig Kjellström
23.04.2018

Networking the IoT with RIOT

Prof. Dr. Thomas Schmidt
20.11.2017

Analyzing Human Behavior in Video Sequences

Prof. Dr. Jürgen Gall
06.11.2017

Jointly Representing Images and Text: Dependency Graphs, Word Senses, and Multimodal Embeddings

Prof. Dr. Frank Keller
17.07.2017

Machine Learning and Knowledge Extraction

Prof. Dr. Andreas Holzinger
19.06.2017

Adaptive Language Technologies

Prof. Dr. Chris Biemann
29.05.2017

Visually Browsing Millions of Images using Image Graphs

Kai Uwe Barthel
28.11.2016

Making Semantic Technology Intelligent

Dr. Gerard de Melo
14.11.2016

Cognitive Computer Vision for Mobile Systems

Prof. Dr. Simone Frintrop
04.07.2016

Graph-Mining zur Schwachstellensuche

Prof. Dr. Konrad Rieck
03.05.2016

Embodied Affective Decision Making in Robots

Dr. Robert Lowe
25.01.2016

The Challenges of Affect Detection

Nicole Novielli
16.04.2015

Developmental robotics - From babies to Robots

Angelo Cangelosi
27.10.2014

Fooling your Senses for (Super-) Natural User Interfaces

Prof. Dr. Frank Steinicke
20.10.2014

Social media for developers: How tools shape the way we work

Dr. Leif Singer
10.07.2014

Machine Learning of Motor Skills for Robotics

Jan Peters
10.06.2014

Die Hamburg Bit-Bots: Aufbruch ins Unbekannte

N. N.
17.03.2014

Logic for Design Science Research Theory Accumulation

Tuure Tuunanen