Journal ArticleDOI
Learning long-term dependencies with gradient descent is difficult
TLDR
This work shows why gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases, and exposes a trade-off between efficient learning by gradient descent and latching on information for long periods.Abstract:
Recurrent neural networks can be used to map input sequences to output sequences, such as for recognition, production or prediction problems. However, practical difficulties have been reported in training recurrent neural networks to perform tasks in which the temporal contingencies present in the input/output sequences span long intervals. We show why gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases. These results expose a trade-off between efficient learning by gradient descent and latching on information for long periods. Based on an understanding of this problem, alternatives to standard gradient descent are considered. >read more
Citations
More filters
Proceedings ArticleDOI
EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding
TL;DR: Eesen as mentioned in this paper proposes a generalized decoding approach based on weighted finite-state transducers (WFSTs), which enables the efficient incorporation of lexicons and language models into CTC decoding.
Journal ArticleDOI
Video Captioning With Attention-Based LSTM and Semantic Consistency
TL;DR: A novel end-to-end framework named aLSTMs, an attention-based LSTM model with semantic consistency, to transfer videos to natural sentences with competitive or even better results than the state-of-the-art baselines for video captioning in both BLEU and METEOR.
Journal ArticleDOI
Remaining useful life estimation of engineered systems using vanilla LSTM neural networks
TL;DR: This paper aims to propose utilizing vanilla LSTM neural networks to get good RUL prediction accuracy which makes the most of long short-term memory ability, in the cases of complicated operations, working conditions, model degradations and strong noises.
Proceedings Article
Effective LSTMs for Target-Dependent Sentiment Classification
TL;DR: Two target dependent long short-term memory models, where target information is automatically taken into account, are developed, which achieve state-of-the-art performances without using syntactic parser or external sentiment lexicons.
Journal ArticleDOI
Deep Learning in Drug Discovery.
TL;DR: An overview of this emerging field of molecular informatics, the basic concepts of prominent deep learning methods are presented, and motivation to explore these techniques for their usefulness in computer‐assisted drug discovery and design is offered.
References
More filters
Journal ArticleDOI
Optimization by Simulated Annealing
TL;DR: There is a deep and useful connection between statistical mechanics and multivariate or combinatorial optimization (finding the minimum of a given function depending on many parameters), and a detailed analogy with annealing in solids provides a framework for optimization of very large and complex systems.
Book ChapterDOI
Learning internal representations by error propagation
TL;DR: This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion.
Book
Learning internal representations by error propagation
TL;DR: In this paper, the problem of the generalized delta rule is discussed and the Generalized Delta Rule is applied to the simulation results of simulation results in terms of the generalized delta rule.
Journal ArticleDOI
A learning algorithm for continually running fully recurrent neural networks
Ronald J. Williams,David Zipser +1 more
TL;DR: The exact form of a gradient-following learning algorithm for completely recurrent networks running in continually sampled time is derived and used as the basis for practical algorithms for temporal supervised learning tasks.
Journal ArticleDOI
Minimizing multimodal functions of continuous variables with the “simulated annealing” algorithm—Corrigenda for this article is available here
TL;DR: A new global optimization algorithm for functions of continuous variables is presented, derived from the “Simulated Annealing” algorithm recently introduced in combinatorial optimization, which is quite costly in terms of function evaluations, but its cost can be predicted in advance, depending only slightly on the starting point.