Deep neural networks perform better in most specific single tasks than humans. but it is hard to handle a sequence of new tasks from different domains. The deep learning-based models always need to remember the parameters of the learned tasks to perform well in the new tasks and forfeit the ability to generalize from previous data. which is inconsistent with human learning. https://www.bekindtopets.com/limited-value-SharkBite-U648LF-Lead-Free-Brass-Push-to-Connect-45-Degree-Elbow-1-2-x-1-2-mega-super/