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
Journal ArticleDOI
Artificial neural network applications in the calibration of spark-ignition engines: An overview
Richard Fiifi Turkson,Richard Fiifi Turkson,Fuwu Yan,Mohamed Kamal Ahmed Ali,Mohamed Kamal Ahmed Ali,Jie Hu +5 more
TL;DR: The identified and discussed applications include system identification for rapid prototyping, virtual sensing, use of neural networks as look-up table surrogates, emerging control strategies and On-Board Diagnostic applications.
Book ChapterDOI
Open-World Stereo Video Matching with Deep RNN
TL;DR: In this article, a recurrent neural network (RNN) is proposed to predict a depth map at each frame without a pre-training process, and without the need of ground-truth depth-maps as supervision.
Journal ArticleDOI
A dual-stage attention-based Conv-LSTM network for spatio-temporal correlation and multivariate time series prediction
Proceedings ArticleDOI
An evolutionary optimization framework for neural networks and neuromorphic architectures
TL;DR: This work describes an EO training framework for a spiking neural network architecture and a neuromorphic architecture, and presents the results of this training framework on four classification data sets and compares those results to other neural network and neuromorphic implementations.
Journal ArticleDOI
An empirical evaluation of deep learning for ICD-9 code assignment using MIMIC-III clinical notes.
TL;DR: In this article, the authors evaluated the performance of deep learning-based systems to automatically map clinical notes to ICD-9 medical codes using the Medical Information Mart for Intensive Care (MIMIC-III) dataset.
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.