Corpus ID: 218628670

Natural Way to Overcome the Catastrophic Forgetting in Neural Networks

@article{Kutalev2020NaturalWT,
  title={Natural Way to Overcome the Catastrophic Forgetting in Neural Networks},
  author={Alexey Kutalev},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.07107}
}
Not so long ago, a method was discovered that successfully overcomes the catastrophic forgetting of neural networks. Although we know about the cases of using this method to preserve skills when adapting pre-trained networks to particular tasks, it has not yet obtained widespread distribution. In this paper, we would like to propose an alternative method of overcoming catastrophic forgetting based on the total absolute signal passing through each connection in the network. This method has a… Expand
1 Citations
An Appraisal of Incremental Learning Methods
  • 1
  • PDF

References

SHOWING 1-8 OF 8 REFERENCES
Catastrophic forgetting in connectionist networks
  • R. French
  • Psychology, Medicine
  • Trends in Cognitive Sciences
  • 1999
  • 690
  • PDF
Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem
  • 1,552
Prolonged myelination in human neocortical evolution
  • 374
  • PDF
Overcoming catastrophic forgetting in neural networks
  • 95
  • Highly Influential
An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv:1312.6211
  • 2015