NaN.

Sequence to Sequence Learning with Neural Networks[ Edit ]

From Deep Learning Top Research Papers List course

Choose your learning format:

Article

Cards

This article is a summary of the following research paper from Google, which used an 8-layer LSTM neural network for achieving state-of-the-art results in language translation.

Introduction

The paper proposes a general and end-to-end approach for sequence learning that uses two deep LSTMs, one to map input sequence to vector space and another to map vector to the output sequence.
For sequence learning, Deep Neural Networks (DNNs) requires the dimensionality of input and output sequences be known and fixed. This limitation is overcome by using the two LSTMs.

Category: Deep Learning