Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Introduction to Machine Learning with Robots and Playful Learning

: Olari, Victoriya; Cvejoski, Kostadin; Eide, Øyvind

Association for the Advancement of Artificial Intelligence -AAAI-:
AAAI-21, IAAI-21, EAAI-21. Proceedings : A Virtual Conference, February 2-9, 2021, Thirty-Fifth AAAI Conference on Artificial Intelligence, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, The Eleventh Symposium on Educational Advances in Artificial Intelligence
Palo Alto/Calif.: AAAI Press, 2021 (AAAI Technical Tracks Vol.35, Nr.17)
ISBN: 978-1-57735-866-4
Conference on Artificial Intelligence (AAAI) <35, 2021, Online>
Conference on Innovative Applications of Artificial Intelligence (IAAI) <33, 2021, Online>
Symposium on Educational Advances in Artificial Intelligence (EAAI) <11, 2021, Online>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
01-S18038B; ML2R
Fraunhofer IAIS ()
AI Education; machine learning; robotics; neural networks; Q-Learning; playful learning; clustering; K-means Algorithm; Open Roberta Lab; Constructionism; AI Teaching

Inspired by explanations of machine learning concepts in childrens books, we developed an approach to introduce supervised, unsupervised, and reinforcement learning using a block-based programming language in combination with the benefits of educational robotics. Instead of using blocks as high-end APIs to access AI cloud services or to reproduce the machine learning algorithms, we use them as a means to put the student in the algorithms shoes. We adapt the training of neural networks, Q-learning, and k-means algorithms to a design and format suitable for children and equip the students with hands-on tools for playful experimentation. The children learn about direct supervision by modifying the weights in the neural networks and immediately observing the effects on the simulate d robot. Following the ideas of constructionism, they experience how the algorithms and underlying machine learning concepts work in practice. We conducted and evaluated this approach with students in primary, middle, and high school. All the age groups perceived the topics to be very easy to moderately hard to grasp. Younger students experienced direct supervision as challenging, whereas they found Q-learning and k-means algorithms much more accessible. Most high-school students could cope with all the topics without particular difficulties.