Out-of-distribution forgetting: vulnerability of continual learning to intra-class distribution shift

no code implementations • 1 Jun 2023 • Liangxuan Guo, Yang Chen, Shan Yu

In this work, we reported a special form of catastrophic forgetting raised by the OOD problem in continual learning settings, and we named it out-of-distribution forgetting (OODF).

Continual Learning Image Classification

Emergence of Symbols in Neural Networks for Semantic Understanding and Communication

no code implementations • 13 Apr 2023 • Yang Chen, Liangxuan Guo, Shan Yu

The capacity to generate meaningful symbols and effectively employ them for advanced cognitive processes, such as communication, reasoning, and planning, constitutes a fundamental and distinctive aspect of human intelligence.