"[I]n the public university setting, student disagreement with a professor's academic speech on an issue of public concern cannot alter the Pickering analysis in the government's favor." A short ...

Abstract: Continual learning (CL) studies the problem of learning to accumulate knowledge over time from a stream of data. A crucial challenge is that neural networks suffer from performance ...

Abstract: Class-incremental learning (CIL) aims to learn a family of classes incrementally with data available in order rather than training all data at once. One main drawback of CIL is that standard ...