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
How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies
TL;DR: This work gives empirical justification to the hypothesis that similar improvements in learning long-term dependencies can be achieved with other classes of recurrent neural network axchitectures simply by increasing the order of the embedded memory.
Posted Content
Second-Order Optimization for Non-Convex Machine Learning: An Empirical Study
TL;DR: Detailed empirical evaluations of a class of Newton-type methods, namely sub-sampled variants of trust region (TR) and adaptive regularization with cubics (ARC) algorithms, for non-convex ML problems demonstrate that these methods not only can be computationally competitive with hand-tuned SGD with momentum, obtaining comparable or better generalization performance, but also they are highly robust to hyper-parameter settings.
Proceedings ArticleDOI
Interpretable Predictions of Clinical Outcomes with An Attention-based Recurrent Neural Network
Ying Sha,May D. Wang +1 more
TL;DR: A gated recurrent unit-based recurrent neural network with hierarchical attention for mortality prediction and the prediction accuracy of the model outperforms baseline models is found and the interpretability is demonstrated in visualizations.
Posted Content
Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors
TL;DR: A deep network architecture using residual bidirectional long short-term memory (LSTM) is proposed, aiming to enhance the recognition rate.
Book ChapterDOI
Multimodal Emotion Recognition Using Deep Neural Networks
TL;DR: A Bimodal-LSTM model is introduced to take temporal information into account for emotion recognition with multimodal signals and it outperforms other state-of-the-art methods.
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.