Under review as a conference paper at ICLRM ETA L EARNING S HARED H IERARCHIES Jonathan Ho, Xi Chen, Pieter Abbeel UC Berkeley, Department of Electrical Engineering and Computer Science

First Page		Document Content
Date: 2017-10-26 20:31:00 Machine learning Artificial intelligence Learning Statistical randomness Q-learning Metalearning Reinforcement learning Artificial neural network Meta learning Multi-armed bandit Markov decision process Feature learning		Under review as a conference paper at ICLRM ETA L EARNING S HARED H IERARCHIES Jonathan Ho, Xi Chen, Pieter Abbeel UC Berkeley, Department of Electrical Engineering and Computer Science Add to Reading List Source URL: arxiv.org Download Document from Source Website File Size: 2,07 MB Share Document on Facebook

	Natural Language to Structured Query Generation via Meta-Learning Po-Sen Huang 1 Chenglong Wang 2 Rishabh Singh 3 * Wen-tau Yih 4 Xiaodong He 5 * 1. Introduction Conventional supervised training is a pervasive paradigm DocID: 1xUL3 - View Document
	On First-Order Meta-Learning Algorithms arXiv:1803.02999v3 [cs.LG] 22 Oct 2018 Alex Nichol and Joshua Achiam and John Schulman OpenAI DocID: 1xUe9 - View Document
	Natural Language to Structured Query Generation via Meta-Learning Po-Sen Huang? , Chenglong Wang† , Rishabh Singh? , Wen-tau Yih‡ , Xiaodong He∗ ? Microsoft Research, † University of Washington, ‡ Allen Instit DocID: 1xTvC - View Document
	Meta-Learning as a Collaborative Filtering Problem Mustafa Misir, Mich`ele Sebag MetaSel@ECAI 2014, August 2014 DocID: 1uUlV - View Document
	Learning to learn: meta-learning for medical image segmentation Imagine you have experience with two medical imaging applications (for example, segmentation in brain MR images, and segmentation of cells in histopatholog DocID: 1umye - View Document