Associative Long Short-Term Memory
Neural and Evolutionary Computing
2016-05-20 v2
Abstract
We investigate a new method to augment recurrent neural networks with extra memory without increasing the number of network parameters. The system has an associative memory based on complex-valued vectors and is closely related to Holographic Reduced Representations and Long Short-Term Memory networks. Holographic Reduced Representations have limited capacity: as they store more information, each retrieval becomes noisier due to interference. Our system in contrast creates redundant copies of stored information, which enables retrieval with reduced noise. Experiments demonstrate faster learning on multiple memorization tasks.
Cite
@article{arxiv.1602.03032,
title = {Associative Long Short-Term Memory},
author = {Ivo Danihelka and Greg Wayne and Benigno Uria and Nal Kalchbrenner and Alex Graves},
journal= {arXiv preprint arXiv:1602.03032},
year = {2016}
}
Comments
ICML-2016