Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Neural Turing Machines

About

We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples.

Alex Graves, Greg Wayne, Ivo Danihelka• 2014

Related benchmarks

TaskDatasetResultRank
Natural Language InferenceSNLI (test)
Accuracy81.8
681
Language ModelingWikiText-103 (test)
Perplexity48.7
524
Sequential Image ClassificationPMNIST (test)
Accuracy (Test)90.9
77
Question AnsweringbAbI (test)
Mean Error31.42
54
Question AnsweringbAbI 10k (test)
Task 1: 1 Supporting Fact Error31.5
15
Copying TaskCopying Task 50 (train)
CE0.00e+0
9
Copying TaskCopying Task 200 (test)
Cross-Entropy2.54
9
Synthetic CopySynthetic Copy L=50 (test)
Test Accuracy40.1
6
Synthetic ReverseSynthetic Reverse L=50 (test)
Test Accuracy61.1
6
Synthetic CopySynthetic Copy L=100 (test)
Test Accuracy11.8
6
Showing 10 of 12 rows

Other info

Follow for update