papers AI Learner
The Github is limit! Click to go to the new site.

Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems

2016-09-20
Colin Raffel, Daniel P. W. Ellis

Abstract

We propose a simplified model of attention which is applicable to feed-forward neural networks and demonstrate that the resulting model can solve the synthetic “addition” and “multiplication” long-term memory problems for sequence lengths which are both longer and more widely varying than the best published results for these tasks.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1512.08756

PDF

https://arxiv.org/pdf/1512.08756


Similar Posts

Comments