2018 DynamicNeuralTuringMachinewithC

• (Gulcehre et al., 2018) ⇒ Caglar Gulcehre, Sarath Chandar, Kyunghyun Cho, and Yoshua Bengio. (2018). “Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes.” In: Neural Computation Journal, 30(4). ISBN:0899-7667 doi:10.1162/neco_a_01060

Subject Headings: Dynamic Neural Turing Machine, Neural Turing Machine.

Notes

Previous version, also referred as:

• (Gulcehre et al., 2016) ⇒ Caglar Gulcehre, Sarath Chandar, Kyunghyun Cho, and Yoshua Bengio. (2016). “Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes.”

Cited By

• http://scholar.google.com/scholar?q=%222018%22+Dynamic+Neural+Turing+Machine+with+Continuous+and+Discrete+Addressing+Schemes
• http://scholar.google.com/scholar?q=%222016%22+Dynamic+Neural+Turing+Machine+with+Soft+and+Hard+Addressing+Schemes
• http://dl.acm.org/citation.cfm?id=3243583.3243584&preflayout=flat#citedby

Quotes

Abstract

We extend the neural Turing machine (NTM) model into a dynamic neural Turing machine (D-NTM) by introducing trainable address vectors. This addressing scheme maintains for each memory cell two separate vectors, content and address vectors. This allows the D-NTM to learn a wide variety of location-based addressing strategies, including both linear and nonlinear ones. We implement the D-NTM with both continuous and discrete read and write mechanisms. We investigate the mechanisms and effects of learning to read and write into a memory through experiments on Facebook bAbI tasks using both a feedforward and GRU controller. We provide extensive analysis of our model and compare different variations of neural Turing machines on this task. We show that our model outperforms long short-term memory and NTM variants. We provide further experimental results on the sequential MNIST, Stanford Natural Language Inference, associative recall, and copy tasks.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2018 DynamicNeuralTuringMachinewithC	Yoshua Bengio Kyunghyun Cho Caglar Gulcehre Sarath Chandar			Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes				10.1162/neco_a_01060		2018