Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks Brenden Lake 1 2 Marco Baroni 2 Abstract

First Page		Document Content
Date: 2018-06-06 16:22:27 Artificial neural networks Computational neuroscience Cognitive science Applied mathematics Cybernetics Cognition Computational statistics Artificial intelligence Recurrent neural network Deep learning Neural network Language model		Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks Brenden Lake 1 2 Marco Baroni 2 Abstract Add to Reading List Source URL: cims.nyu.edu Download Document from Source Website File Size: 1,01 MB Share Document on Facebook

	Journal of Computational Neuroscience 18, 105–121, 2005 c 2005 Springer Science + Business Media, Inc. Manufactured in The Netherlands. A Cellular Mechanism for Graded Persistent Activity in a Model Neuron and Its Im DocID: 1vcJi - View Document
	munich Bernstein Center for Computational Neuroscience Munich DocID: 1vcv8 - View Document
	Blending computational and experimental neuroscience DocID: 1v9kZ - View Document
	Florentin Wörgötter Bernstein Center for Computational Neuroscience Göttingen Florentin Wörgötter studied biology and mathematics at the University of Düsseldorf, Germany. He received a Ph.D. degree, studying DocID: 1v914 - View Document
	Nonlinear synaptic interaction as a computational resource in the Neural Engineering Framework Andreas Stöckel, Aaron R. Voelker, Chris Eliasmith Centre for Theoretical Neuroscience, University of Waterloo {astoecke, ar DocID: 1uuia - View Document