Toward Training Recurrent Neural Networks for Lifelong Learning

DOI10.1162/neco_a_01246zbMath1473.68168arXiv1811.07017OpenAlexW2983826605WikidataQ91189938 ScholiaQ91189938MaRDI QIDQ5131161

Yoshua Bengio, Shagun Sodhani, Sarath Chandar

Publication date: 2 November 2020

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.07017

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Uses Software

• PyTorch
• ImageNet
• Adam
• CORe50
• iCaRL
• Net2Net
• FitNets

Cites Work

• CHILD: A first step towards continual learning
• Duality in quadratic programming
• Overcoming catastrophic forgetting in neural networks
• Unnamed Item
• Unnamed Item