Block Neural Network Avoids Catastrophic Forgetting When Learning Multiple Task
Guglielmo Montone, John Kevin O'Regan, Alexander V. Terekhov · arXiv (Cornell University) · 2017
In the present work we propose a Deep Feed Forward network architecture which can be trained according to a sequential learning paradigm, where tasks of increasing difficulty are learned sequentially, yet avoiding catastrophic forgetting. The proposed architecture can re-use the features learned on previous tasks in a new task when the old tasks and the new one are related. The architecture needs fewer computational resources (neurons and connections) and less data for learning the new task than a network trained from scratch