BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://github.com/derhansen/sf_event_mgt
METHOD:PUBLISH
BEGIN:VEVENT
UID:7113-2022@rg-bremen-oldenburg.gi.de
CLASS: PUBLIC
SUMMARY:Lifelong Learning Machines: The Quest for Sustainable Adaptation in
  a World of Unexpected Change
DESCRIPTION:Deep machine learning continues to advance the frontiers of inn
 ovative applications, recently through the rise of generative AI and founda
 tion models. However, as much as their success is astonishing, their highly
  opaque nature continues to entail an increasing amount of scientific and s
 ocio-economic concerns. Many of these considerations seem to derive from a 
 predominantly static workflow and are related to a respective culture of be
 nchmarking. In fact, the machine learning textbooks teach us that an approp
 riate recipe is to acquire training data, select a model, and then tune its
  parameters until a desired performance criterion is reached on a held-out 
 test set. The real world is significantly more ruthless than these crafted 
 benchmarks: data distributions tend to drift, unexpected changes frequently
  arise, and evaluation is seldom as straightforward as pre-defined test set
 s make it out to be. Put into practice, the textbook machine learning appro
 ach thus entails unreasonable amounts of re-training, the produced model ou
 tputs tend to be erratic and unreliable, and the data-hungry and compute-he
 avy development cycle shifts power to the privileged.\n\nInspired by the hu
 man’s remarkable ability to adapt efficiently to a variety of contexts with
 out amassing tremendous amounts of resources, lifelong learning promises to
  surmount many of the aforementioned predicaments. In this talk, I will int
 roduce the elements necessary to shift the prevalent static design towards 
 lifelong machine learning systems. These systems transcend stationary datas
 ets and continually learn in a world full of unknowns, highlighting pivotal
  aspects to render AI systems more adaptive, robust and sustainable. Focusi
 ng on our group’s own key contributions, I will present remedies to enable 
 deep neural networks to successfully handle new situations, to overcome the
  need to store large datasets, and to efficiently incorporate new knowledge
  over time. Importantly, I will highlight our proposed mechanisms to achiev
 e these aspects inherently and synergistically, counteracting the present m
 achine learning trend to alleviate discovered caveats through post-hoc modi
 fications. Finally, I will provide some examples of our pursued application
 s in computer vision to highlight why lifelong learning is key to sustainab
 le adaptation in a world of unexpected changes.\n\nReferent: Prof. Martin M
 undt  *** ANTRITTSVORLESUNG ***\n\nMartin Mundt is the newly appointed Prof
 essor for Lifelong Machine Learning at the University of Bremen. He previou
 sly led an independent research group at the Hessian Center for Artificial 
 Intelligence (hessian.AI) and the Technical Unviersity of Darmstadt, where 
 he was also an interim professor (Vertretungsprofessor). He holds a PhD deg
 ree in Computer Science from Goethe University Frankfurt, and an M.Sc. in P
 hysics. He is also a board member of directors at the non-profit organizati
 on ContinualAI and part of the core-organizer team at Queer in AI. In his r
 esearch, the central goal is to develop AI systems that continue learning t
 hroughout their lifecycles. This capability for lifelong machine learning –
  a key ability of the human brain – is pivotal to render AI systems more ad
 aptive, robust and inclusive. As such, Martin believes that lifelong learni
 ng is an essential missing element to make AI both technologically and soci
 ally more sustainable. These goals are reflected in Martin’s commitment to 
 the research community, for instance, as diversity & inclusion chair of AAA
 I-24 and CoLLAs-25, review-process chair of CoLLAs-24, general chair of the
  CLAI-23 Unconference, and associate editor-in-chief at Pattern Recognition
 . His respective research has received best paper distinctions at ACM FAccT
  2023, outstanding student paper at AISTATS 2024, alongside awards for his 
 PhD thesis and lectures.
LOCATION:Uni Bremen, Cartesium, Rotunde
DTSTAMP:20250507T114530Z
DTSTART:20250520T140000Z
DTEND:20250520T153000Z
END:VEVENT
END:VCALENDAR