BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//scienceofintelligence.de - ECPv6.15.12.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:scienceofintelligence.de
X-ORIGINAL-URL:https://www.scienceofintelligence.de
X-WR-CALDESC:Events for scienceofintelligence.de
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20190331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20191027T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20200329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20201025T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20210328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20211031T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20201105T100000
DTEND;TZID=Europe/Berlin:20201105T110000
DTSTAMP:20260411T044503
CREATED:20201102T111116Z
LAST-MODIFIED:20250604T095834Z
UID:9081-1604570400-1604574000@www.scienceofintelligence.de
SUMMARY:Robert Lange (SCIoI): “Learning Not To Learn\, Nature Versus Nurture In Silico”
DESCRIPTION:Abstract: Animals are equipped with a rich innate repertoire of sensory\, behavioral and motor skills\, which allows them to interact with the world immediately after birth. At the same time\, many behaviors are highly adaptive and can be tailored to specific environments by means of learning and exploration. In this work\, we use mathematical analysis and the framework of meta-learning (or ‘learning to learn’) to answer when it is beneficial to learn such an adaptive strategy and when to hard-code a heuristic behavior. We find that the interplay of ecological uncertainty\, task complexity and the agents’ lifetime has crucial effects on the meta-learned amortized Bayesian inference performed by an agent. There exist two regimes: One in which meta- learning yields a learning algorithm that implements task-dependent exploration and a second regime in which meta-learning imprints a purely exploitative and ‘hard-coded’ behavior. Further analysis reveals that non-adaptive behaviors are not only optimal for aspects of the environment that are stable across individuals\, but also in situations where an adaptation to the environment would in fact be highly beneficial\, but could not be done quickly enough to be exploited within the remaining lifetime. Hard-coded behaviors should hence not only be those that always work\, but also those that are too complex to be learned within a reasonable time frame.\nLink: https://arxiv.org/abs/2010.04466 \nThe Zoom Link will be sent the day before the lecture. (Contact communication@scioi.de for specific questions)
URL:https://www.scienceofintelligence.de/event/thursday-morning-talk-robert-lange-title-learning-not-to-learn-nature-versus-nurture-in-silico/
CATEGORIES:Thursday Morning Talk
ATTACH;FMTTYPE=image/jpeg:https://www.scienceofintelligence.de/wp-content/uploads/2020/03/Robert1-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20201112T100000
DTEND;TZID=Europe/Berlin:20201112T113000
DTSTAMP:20260411T044503
CREATED:20201102T113930Z
LAST-MODIFIED:20240813T105714Z
UID:9084-1605175200-1605180600@www.scienceofintelligence.de
SUMMARY:Heiko Hamann\, Minimize Surprise in Robots: An Innate Motivation for Collective Behavior
DESCRIPTION:Minimize Surprise in Robots: An Innate Motivation for Collective Behavior \nAfter a quick overview of other related research projects in my lab (bio-hybrid systems\, swarm performance\, collective decision-making)\, I will present our work on minimize surprise for multi-robot systems. Each robot has two artificial neural networks\, a world model (“prediction machine”) and a behavioral module (“action selection network”)\, that are trained concurrently. There is no predefined task\, instead the swarm is rewarded for making correct predictions about future sensory input. As an effect\, robots discover behaviors introducing predictable spatiotemporal sensor patterns. I will present simulated results for flocking\, aggregation\, self-assembly\, construction\, and first results using real-world mobile robots. \nThe Zoom Link will be sent the day before the lecture. (Contact communication@scioi.de for specific questions)
URL:https://www.scienceofintelligence.de/event/thursday-morning-talk-heiko-hamann-minimize-surprise-in-robots-an-innate-motivation-for-collective-behavior/
CATEGORIES:Thursday Morning Talk
ATTACH;FMTTYPE=image/jpeg:https://www.scienceofintelligence.de/wp-content/uploads/2019/10/Hamann_800.jpg
END:VEVENT
END:VCALENDAR