Advanced Topics in Continual / Organic Machine Learning

This seminar will be an online seminar (zoom). The seminar is on Wednesdays, 17:30 to 19:00, beginning on the 6th of May. More specific information will be announced in this Illias course. Seminar content: In many areas, neural networks have achieved a performance comparable to or better than that of humans. However, neural networks usually learn in a different way than humans. The neuronal networks are trained with gigantic data sets and after learning these data sets they are used in production. Humans learn continuously from their interaction with their environment. In organic machine learning, neural networks should learn in the same way as humans. In this seminar, current research results on different aspects of such organic learning neural networks are presented. Possible topics are Reinforcement Learning, integration of knowledge, learning concepts, feedback mechanisms, ...

Zusammenfassung

This seminar will be an online seminar (zoom). The seminar is on Wednesdays, 17:30 to 19:00, beginning on the 6th of May. More specific information will be announced in this Illias course.
Seminar content:
In many areas, neural networks have achieved a performance comparable to or better than that of humans. However,
neural networks usually learn in a different way than humans. The neuronal networks are trained with gigantic
data sets and after learning these data sets they are used in production. Humans learn continuously from their interaction with their
environment. In organic machine learning, neural networks should learn in the same way as humans.
In this seminar, current research results on different aspects of such organic learning
neural networks are presented. Possible topics are Reinforcement Learning, integration of knowledge,
learning concepts, feedback mechanisms, ...

Allgemein

Sprache
Deutsch
Copyright
This work has all rights reserved by the owner.

Verfügbarkeit

Zugriff
Unbegrenzt – wenn online geschaltet
Aufnahmeverfahren
Sie müssen einen Aufnahmeantrag stellen, um in den Kurs aufgenommen zu werden. Beschreiben Sie im Feld Nachricht, warum Sie beitreten möchten. Sobald Ihr Antrag angenommen oder abgelehnt wurde, erhalten Sie eine Benachrichtigung.
Zeitraum für Beitritte
Bis: 21. Mai 2020, 18:00
Freie Plätze
0
Spätester Kursaustritt
21. Mai 2020

Für Kursadministratoren freigegebene Daten

Daten des Persönlichen Profils
Anmeldename
Vorname
Nachname
E-Mail
Matrikelnummer

Zusätzliche Informationen

Objekt-ID
1554877