[eas_cs_seminars] 21st March 2017
Luca Rossi l.rossi at aston.ac.ukMon Mar 20 13:03:53 GMT 2017
- Previous message: [eas_cs_seminars] 21st March 2017
- Next message: [eas_cs_seminars] 28th March 2017
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Hi all, This is a reminder of tomorrow's talk "Online Ensemble Learning of Data Streams with Gradually Evolved Classes" Dr. Leandro Minku ( http://www.cs.le.ac.uk/people/llm11/) (mb220, 2pm to 3pm). Best, Luca On 16 March 2017 at 15:16, Luca Rossi <l.rossi at aston.ac.uk> wrote: > Dear all, > > The next CS seminar will be on Tuesday 21/03 from 2pm to 3pm in MB220. > Dr. Leandro Minku (http://www.cs.le.ac.uk/people/llm11/) will be giving a > talk titled "Online Ensemble Learning of Data Streams with Gradually > Evolved Classes". > > Abstract: > In machine learning, class evolution is the phenomenon of class emergence > and disappearance. It is likely to occur in many data stream problems, > which are problems where additional training data become available over > time. For example, in the problem of classifying tweets according to their > topic, new topics may emerge over time, and certain topics may become > unpopular and not discussed anymore. Therefore, class evolution is an > important research topic in the area of learning data streams. Existing > work implicitly regards class evolution as an abrupt change. However, in > many real world problems, classes emerge or disappear gradually. This gives > rise to extra challenges, such as non-stationary imbalance ratios between > the different classes in the problem. In this talk, I will present an > ensemble approach able to deal with gradually evolved classes. In order to > quickly adjust to class evolution, the ensemble maintains a base learner > for each class and dynamically creates, updates and (de)activates base > learners whenever new training data become available. It also uses a > dynamic undersampling technique in order to deal with the non-stationary > class imbalance present in this type of problem. Empirical studies > demonstrate the effectiveness of the proposed approach in various class > evolution scenarios in comparison with existing class evolution approaches. > > See you all next week, > Luca > -- > Luca Rossi > > Lecturer in Computer Science > School of Engineering and Applied Science > Aston University > Web: http://www.cs.aston.ac.uk/~rossil/ > <http://www.cs.bham.ac.uk/~rossil/> > -- Luca Rossi Lecturer in Computer Science School of Engineering and Applied Science Aston University Web: http://www.cs.aston.ac.uk/~rossil/ <http://www.cs.bham.ac.uk/~rossil/> -------------- next part -------------- An HTML attachment was scrubbed... URL: http://lists.aston.ac.uk/pipermail/eas_cs_seminars/attachments/20170320/0188f3fd/attachment.html
- Previous message: [eas_cs_seminars] 21st March 2017
- Next message: [eas_cs_seminars] 28th March 2017
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the eas_cs_seminars mailing list