Learning Temporal Dependencies in Data Using a DBN-BLSTM
Machine Learning
2014-12-25 v2 Neural and Evolutionary Computing
Abstract
Since the advent of deep learning, it has been used to solve various problems using many different architectures. The application of such deep architectures to auditory data is also not uncommon. However, these architectures do not always adequately consider the temporal dependencies in data. We thus propose a new generic architecture called the Deep Belief Network - Bidirectional Long Short-Term Memory (DBN-BLSTM) network that models sequences by keeping track of the temporal information while enabling deep representations in the data. We demonstrate this new architecture by applying it to the task of music generation and obtain state-of-the-art results.
Cite
@article{arxiv.1412.6093,
title = {Learning Temporal Dependencies in Data Using a DBN-BLSTM},
author = {Kratarth Goel and Raunaq Vohra},
journal= {arXiv preprint arXiv:1412.6093},
year = {2014}
}
Comments
6 pages, 2 figures, 1 table, ICLR 2015 conference track submission under review