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
Decision support from financial disclosures with deep neural networks and transfer learning
Mathias Kraus,Stefan Feuerriegel +1 more
TL;DR: The use of deep neural networks for financial decision support is studied and a higher directional accuracy as compared to traditional machine learning when predicting stock price movements in response to financial disclosures is revealed.
Proceedings ArticleDOI
Using Structured Events to Predict Stock Price Movement: An Empirical Investigation
TL;DR: This work proposes to adapt Open IE technology for event-based stock price movement prediction, extracting structured events from large-scale public news without manual efforts, and outperforms bags-of-words-based baselines and previous systems trained on S&P 500 stock historical data.
Journal ArticleDOI
Short-term photovoltaic power forecasting based on long short term memory neural network and attention mechanism
TL;DR: A hybrid ensemble deep learning framework is proposed to forecast short-term photovoltaic power generation in a time series manner and adopted the attention mechanism for the two LSTM neural networks to adaptively focus on input features that are more significant in forecasting.
Posted Content
Model-Ensemble Trust-Region Policy Optimization
TL;DR: The authors proposed to use an ensemble of models to maintain the model uncertainty and regularize the learning process, which significantly reduces the sample complexity compared to model-free deep RL methods on challenging continuous control benchmark tasks.
Proceedings Article
Full-capacity unitary recurrent neural networks
TL;DR: This work provides a theoretical argument to determine if a unitary parameterization has restricted capacity, and shows how a complete, full-capacity unitary recurrence matrix can be optimized over the differentiable manifold of unitary matrices.
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.