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
Day-Ahead Solar Irradiance Forecasting for Microgrids Using a Long Short-Term Memory Recurrent Neural Network: A Deep Learning Approach
Munir Husein,Il-Yop Chung +1 more
TL;DR: In this article, the authors proposed an hourly day-ahead solar irradiance forecasting model that uses only widely available weather data, namely, dry-bulb temperature, dew-point temperature, and relative humidity.
Book ChapterDOI
A Survey of Design Techniques for Conversational Agents
TL;DR: Various chatbot design techniques, classification of chatbot and discussion on how the modern chatbots have evolved from simple pattern matching, retrieval based model to modern complex knowledge based models are discussed.
Proceedings ArticleDOI
Deep-FSMN for Large Vocabulary Continuous Speech Recognition
TL;DR: DFSMN as mentioned in this paper introduces skip connections between memory blocks in adjacent layers, which enable the information flow across different layers and thus alleviate the gradient vanishing problem when building very deep structure.
Journal ArticleDOI
An ensemble deep learning approach for driver lane change intention inference
TL;DR: A vision-based intention inference system that focuses on the highway lane change maneuvers and a novel ensemble bi-directional recurrent neural network model with Long Short-Term Memory units is proposed to deal with the time-series driving sequence and the temporal behavioral patterns.
Journal ArticleDOI
Reservoir computing with a single delay-coupled non-linear mechanical oscillator
TL;DR: The delay-coupled electromechanical system performed well on time series classification tasks, with error rates below 0.1% for the 1st, 2nd, and 3rd order parity benchmarks and an accuracy of 78 ± 2 for the TI-46 spoken word recognition benchmark.
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.