[Adapt] [Seminar] iCaRL: Incremental Classifier and Representation Learning

[周泽林]

Hi Adapters,


A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. When   data of different classes are not available at the same time but come sequentially, a qualified class-incremental algorithm is supposed to handle incoming new classes while sustain performance on old classes. iCaRL allows learning in such a class- incremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively. In this talk, I will present the intuitions and approaches of iCaRL.



会议主题：ADAPT seminar
会议时间：2022/06/01 16:00-18:00 (GMT+08:00) 中国标准时间 - 北京

点击链接入会，或添加至会议列表：
https://meeting.tencent.com/dm/ZnnkRn70WHDe

#腾讯会议：599-899-699

复制该信息，打开手机腾讯会议即可参与

Time: Wed 4:00pm

Venue: Tencent meeting 599-899-699


Hope you enjoy it!


Best regards,
Zelin
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20220601/79099d8d/attachment.htm>