![AImageLab](https://aimagelab.ing.unimore.it/imagelab/images/header_aimagelab.png)
Back to ImageLab research fields
Research on Continual Learning
General Continual Learning
![continual_learning_notext continual_learning_notext](https://aimagelab.ing.unimore.it/imagelab/uploadedImages/000579_thumb.jpg)
Neural networks are known to suffer from the infamous issue of Catastrophic Inference when their training data shifts in distribution. Continual Learning (CL) is a branch of Machine Learning that aims at training systems that overcome this problem. As the majority of the proposed evaluation settings for CL fails at encompassing the properties of a practical scenario, we strive to address General Continual Learning (GCL), a setting in which both domain and class distributions shift either gradually or suddenly.