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
A Study of the Recurrent Neural Network Encoder-Decoder for Large Vocabulary Speech Recognition
TL;DR: This paper studies the RNN encoder-decoder approach for large vocabulary end-to-end speech recognition, whereby an encoder transforms a sequence of acoustic vectors into a sequences of feature representations, from which a decoder recovers asequence of words.
Journal ArticleDOI
Review on deep learning applications in frequency analysis and control of modern power system
TL;DR: In this article, the authors reviewed the history, state-of-the-art and the future of the DL's application in power system frequency analysis and control, and the application status of DL in frequency situation awareness, frequency security and stability assessment, and frequency regulation and control were summarized.
Journal ArticleDOI
Review on deep learning applications in frequency analysis and control of modern power system
TL;DR: In this article , the authors reviewed the history, state-of-the-art and the future of the DL's application in power system frequency analysis and control, and the application status of DL in frequency situation awareness, frequency security and stability assessment, and frequency regulation and control.
Book ChapterDOI
LSTM Recurrent Neural Networks for Short Text and Sentiment Classification
TL;DR: A demonstration of how to classify text using Long Term Term Memory (LSTM) network and their modifications, i.e. Bidirectional LSTM network and Gated Recurrent Unit, and the superiority of this method over other algorithms for text classification is presented.
Proceedings ArticleDOI
DeviceMien: network device behavior modeling for identifying unknown IoT devices
TL;DR: A probabilistic framework for providing meaningful feedback in device identification, particularly when the device has not been previously observed is introduced.
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.