Continual Learning with Quasi-Newton Methods
Copyright policy )Continual Learning with Quasi-Newton Methods
<p>In this paper, we propose CSQN, a new Continual Learning (CL) method which considers Quasi-Newton methods, more specifically, Sampled Quasi-Newton methods, to extend EWC.</p> <p>EWC uses a Bayesian framework to estimate which parameters are important to previous tasks, and it punishes changes made to these parameters. However, it assumes that parameters are independent, as it does not consider interactions between parameters. With CSQN, we aim to overcome this.</p>
FOS: Computer and information sciences, Technology, Computer Science - Machine Learning, Science & Technology, Computer Science, Information Systems, Artificial neural networks, catastrophic forgetting, Image and Video Processing (eess.IV), Engineering, Electrical & Electronic, Electrical Engineering and Systems Science - Image and Video Processing, 46 Information and computing sciences, 09 Engineering, TK1-9971, Machine Learning (cs.LG), quasi-Newton methods, Engineering, 10 Technology, Computer Science, Telecommunications, FOS: Electrical engineering, electronic engineering, information engineering, 08 Information and Computing Sciences, Electrical engineering. Electronics. Nuclear engineering, continual learning, 40 Engineering
FOS: Computer and information sciences, Technology, Computer Science - Machine Learning, Science & Technology, Computer Science, Information Systems, Artificial neural networks, catastrophic forgetting, Image and Video Processing (eess.IV), Engineering, Electrical & Electronic, Electrical Engineering and Systems Science - Image and Video Processing, 46 Information and computing sciences, 09 Engineering, TK1-9971, Machine Learning (cs.LG), quasi-Newton methods, Engineering, 10 Technology, Computer Science, Telecommunications, FOS: Electrical engineering, electronic engineering, information engineering, 08 Information and Computing Sciences, Electrical engineering. Electronics. Nuclear engineering, continual learning, 40 Engineering
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!