SERG Seminar

In this edition of our weekly SERG seminar we will have two speakers:

Asato Yamazaki who is a master’s student at Institute of Science Tokyo (former Tokyo Institute of Technology), will present his research on Federated Learning (FL). He will primarily discuss his paper titled “Convergence Improvement by Parameters Exchange in Asynchronous Decentralized Federated Learning for Non-IID Data” and outline his current research direction on the topic.

Clinton Cao, who is doing his PhD with Annibale Pannichella and Sicco Verwer, will talk about fresh results from their latest study. They propose a new search heuristic (MISH) that uses real-time automaton learning to guide the test case generation process within EvoMaster. MISH continuously learns an automation from a stream of log statements and uses the the automaton to define fitness for the test cases.

If you are interested to give a 15 min + 10 talk or host a 25 min discussion session in one of our next meetings, please contact Carolin Brandt via Mattermost or email.