摘要: A central goal of meta-learning is to find a learning rule that enables fast adaptation across a set of tasks, by learning the appropriate inductive bias for that set. Most meta-learning …
harvard.edu
arxiv.org参考文章(25)
Learning to learn Learning to learn. pp. 354- 354 ,(1998) , 10.1007/978-1-4615-5529-2
Peter Bartlett, M Frean, Llew Mason, Jon Baxter, Functional Gradient Techniques for Combining Hypotheses MIT Press. pp. 221- 246 ,(2000)
Matthew Botvinick, Sergey Bartunov, Daan Wierstra, Adam Santoro, Timothy Lillicrap, Meta-learning with memory-augmented neural networks international conference on machine learning. pp. 1842- 1850 ,(2016)
Matt Botvinick, Remi Munos, Joel Z Leibo, Zeb Kurth-Nelson, Dharshan Kumaran, Charles Blundell, Hubert Soyer, Jane X Wang, Dhruva Tirumala, Learning to reinforcement learn arXiv: Learning. ,(2016)
Ilya Sutskever, Pieter Abbeel, Peter L. Bartlett, Yan Duan, John Schulman, Xi Chen, RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning arXiv: Artificial Intelligence. ,(2016)
Kevin Swersky, Richard S. Zemel, Jake Snell, Prototypical Networks for Few-shot Learning neural information processing systems. ,vol. 30, pp. 4077- 4087 ,(2017)
Ashish Vaswani, Jakob Uszkoreit, Noam Shazeer, Illia Polosukhin, Llion Jones, Niki Parmar, Aidan N. Gomez, Lukasz Kaiser, Attention Is All You Need arXiv: Computation and Language. ,(2017)
Hugo Larochelle, Sachin Ravi, Optimization as a Model for Few-Shot Learning international conference on learning representations. ,(2017)
Pieter Abbeel, Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, A Simple Neural Attentive Meta-Learner international conference on learning representations. ,(2018)
Shimon Whiteson, Katja Hofmann, Vitaly Kurin, Luisa Zintgraf, Kyriacos Shiarli, Fast Context Adaptation via Meta-Learning international conference on machine learning. pp. 7693- 7702 ,(2019)