English

Block Neural Network Avoids Catastrophic Forgetting When Learning Multiple Task

Neural and Evolutionary Computing 2017-11-29 v1 Machine Learning Machine Learning

Abstract

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

Keywords

Cite

@article{arxiv.1711.10204,
  title  = {Block Neural Network Avoids Catastrophic Forgetting When Learning Multiple Task},
  author = {Guglielmo Montone and J. Kevin O'Regan and Alexander V. Terekhov},
  journal= {arXiv preprint arXiv:1711.10204},
  year   = {2017}
}
R2 v1 2026-06-22T22:59:11.469Z