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
Real-time crash risk prediction on arterials based on LSTM-CNN.
TL;DR: The findings indicate the promising performance of using LSTM-CNN to predict real-time crash risk on arterials and suggest that the proposed model outperforms others in terms of Area Under the Curve (AUC) value, sensitivity, and false alarm rate.
Journal ArticleDOI
A Hybrid Spectral Clustering and Deep Neural Network Ensemble Algorithm for Intrusion Detection in Sensor Networks
TL;DR: Experimental results indicate that the SCDNN classifier not only performs better than backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF) and Bayes tree models in detection accuracy and the types of abnormal attacks found, but also provides an effective tool of study and analysis of intrusion detection in large networks.
Proceedings ArticleDOI
Rumor Detection with Hierarchical Social Attention Network
TL;DR: A novel hierarchical neural network combined with social information (HSA-BLSTM) is proposed, which first builds a hierarchical bidirectional long short-term memory model for representation learning and incorporates the social contexts into the network via attention mechanism.
Journal ArticleDOI
Android malware detection based on system call sequences and LSTM
TL;DR: A novel detection method based on deep learning is proposed to distinguish malware from trusted applications by treating one system call sequence as a sentence in the language and constructing a classifier based on the Long Short-Term Memory language model.
BookDOI
Deep Learning and Convolutional Neural Networks for Medical Image Computing
TL;DR: The impact of deep learning on automated disease detection and organ and lesion segmentation and the remaining knowledge gaps that must be overcome to achieve clinician-level performance of automated medical image processing systems are discussed.
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.