What is Embodiment, and How Does It Affect the Way We Function?
Prof. Hedvig Kjellström
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.
- Deep Machines That Know When They Do not Know20.05.2019
- Opportunistic Networks - Challenges and Opportunities06.05.2019
- Known Operator Learning? A new Paradigm for Machine Learning in Signal Processing & Physics15.04.2019
- Empirical Studies into Modelling in Software Development in the Age of Big Data and AI01.04.2019
- The innovations, industry problems, and research challenges open source has given us28.01.2019
- Exploring Server-side Blocking of Regions10.12.2018
- Microarchitectural Attacks on modern CPUs26.11.2018
- Language dynamics in social media22.10.2018
- Imitation learning, zero-shot learning and automated fact checking09.07.2018
- An Integrative, Event-Predictive Perspective on Cognition: Behavioral Evidence and Artificial Neural Network Models25.06.2018
- Wem gehören die Daten? Zugangs- und Verfügungsmodelle in der Datenökonomie18.06.2018
- What is Embodiment, and How Does It Affect the Way We Function?07.05.2018
- Networking the IoT with RIOT23.04.2018
- Analyzing Human Behavior in Video Sequences20.11.2017
- Jointly Representing Images and Text: Dependency Graphs, Word Senses, and Multimodal Embeddings06.11.2017
- Machine Learning and Knowledge Extraction17.07.2017
- Adaptive Language Technologies19.06.2017
- Visually Browsing Millions of Images using Image Graphs29.05.2017
- Making Semantic Technology Intelligent28.11.2016
- Cognitive Computer Vision for Mobile Systems14.11.2016
- Graph-Mining zur Schwachstellensuche04.07.2016
- Embodied Affective Decision Making in Robots03.05.2016
- The Challenges of Affect Detection25.01.2016
- Developmental robotics - From babies to Robots16.04.2015
- Fooling your Senses for (Super-) Natural User Interfaces27.10.2014
- Social media for developers: How tools shape the way we work20.10.2014
- Machine Learning of Motor Skills for Robotics10.07.2014
- Die Hamburg Bit-Bots: Aufbruch ins Unbekannte10.06.2014
- Logic for Design Science Research Theory Accumulation17.03.2014