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
Biomedical named entity recognition using deep neural networks with contextual information
Hyejin Cho,Hyunju Lee +1 more
TL;DR: The proposed approach is robust in recognizing biological entities in text by incorporating n-grams with bi-directional long short-term memory (BiLSTM) and CRF and it is concluded that the method significantly improves performance on biomedical NER tasks.
Journal ArticleDOI
Efficient In-Loop Filtering Based on Enhanced Deep Convolutional Neural Networks for HEVC
TL;DR: An efficient in-loop filtering algorithm based on the enhanced deep convolutional neural networks (EDCNN) for significantly improving the performance of in- loop filtering in HEVC is proposed.
Posted Content
Survey on Deep Neural Networks in Speech and Vision Systems
TL;DR: This survey presents a review of state-of-the-art deep neural network architectures, algorithms, and systems in vision and speech applications from the perspectives of both software and hardware systems.
Book ChapterDOI
Deep Learning of Representations
Yoshua Bengio,Aaron Courville +1 more
TL;DR: This chapter reviews the main motivations and ideas behind deep learning algorithms and their representation-learning components, as well as recent results, and proposes a vision of challenges and hopes on the road ahead, focusing on the questions of invariance and disentangling.
Dissertation
Deep Neural Networks for Large Vocabulary Handwritten Text Recognition
TL;DR: It is shown that deep neural networks produce consistent and significant improvements over networks with one or two hidden layers, independently of the kind of neural network, MLP or RNN, and of input, handcrafted features or pixels, and that depth plays an important role in the reduction of the performance gap between the two kinds of inputs.
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.