Advanced Methods for Time Series Prediction Using Recurrent Neural Networks

Time series prediction has important applications in various domains such as medicine, ecology, meteorology, industrial control or finance. Generally the characteristics of the phenomenon which generates the series are unknown. The information available for the prediction is limited to the past values of the series. The relations which describe the evolution should be deduced from these values, in the form of functional relation approximations between the past and the future values. The most usually adopted approach to consider the future values ( ) 1 t x + consists in using a function f which takes as input a time window of fixed size M representing the recent history of the time series. ( ) ( ) ( ) ( ) ( ) [ ] τ − − τ − = 1 M t x , , t x , t x t ... x (1) ( ) ( ) ( ) t f t x x = τ + (2)

• Publication year

  2011

• Venue

  Unknown venue

• Publication date

  2011-02-09

• Fields of study

  Physics, Computer Science

• Identifiers
  DOI 10.5772/16015
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A new boosting algorithm for improved time-series forecasting with recurrent neural networks

  2008cited by this paper
• Study of the Behavior of a New Boosting Algorithm for Recurrent Neural Networks

  2005cited by this paper
• Recurrent Neural Networks with Small Weights Implement Definite Memory Machines

  2003cited by this paper
• Sufficient Conditions for Error Backflow Convergence in Dynamical Recurrent Neural Networks

  2002cited by this paper
• Learning long-term dependencies by the selective addition of time-delayed connections to recurrent neural networks

  2002cited by this paper
• Boosting Methods for Regression

  2002cited by this paper
• Boosting with the L2-loss: regression and classification

  2001cited by this paper
• Local model optimization for time series prediction

  2000cited by this paper
• An algorithm for the addition of time-delayed connections to recurrent neural networks

  2000cited by this paper
• A bounded exploration approach to constructive algorithms for recurrent neural networks

  2000cited by this paper
• Local model optimization for time series prediction.

  2000cited by this paper
• Multi-step-ahead prediction using dynamic recurrent neural networks

  1999influential reference
• Discrete-time backpropagation for training synaptic delay-based artificial neural networks

  1999cited by this paper
• Dynamical recurrent neural networks towards prediction and modeling of dynamical systems

  1999cited by this paper
• A comparison between neural-network forecasting techniques-case study: river flow forecasting

  1999cited by this paper
• On-line learning algorithms for locally recurrent neural networks

  1999cited by this paper
• Computational capabilities of recurrent NARX neural networks

  1997cited by this paper
• A decision-theoretic generalization of on-line learning and an application to boosting

  1997cited by this paper
• Long Short-Term Memory

  1997cited by this paper
• Short term electrical load forecasting with artificial neural networks

  1996cited by this paper
• Boosting the performance of connectionist large vocabulary speech recognition

  1996cited by this paper
• Learning long-term dependencies in NARX recurrent neural networks

  1996influential reference
• Learning a simple recurrent neural state space model to behave like Chua's double scroll

  1995cited by this paper
• Hierarchical Recurrent Neural Networks for Long-Term Dependencies

  1995cited by this paper
• Finite impulse response neural networks with applications in time series prediction

  1994cited by this paper
• Locally recurrent globally feedforward networks: a critical review of architectures

  1994cited by this paper
• Learning long-term dependencies with gradient descent is difficult

  1994cited by this paper
• Time Series Prediction: Forecasting the Future and Understanding the Past

  1994cited by this paper
• Recurrent Neural Networks with Delays

  1994cited by this paper
• Local Feedback Multilayered Networks

  1992cited by this paper
• A structure by which a recurrent neural network can approximate a nonlinear dynamic system

  1991cited by this paper
• Generalization by weight-elimination applied to currency exchange rate prediction

  1991cited by this paper
• Boosting a weak learning algorithm by majority

  1990cited by this paper
• Dynamic recurrent neural networks

  1990cited by this paper
• Nonlinear prediction of chaotic time series

  1989influential reference
• The Strength of Weak Learnability

  1989cited by this paper
• Dynamical Systems and Turbulence

  1982cited by this paper
• Detecting strange attractors in turbulence

  1981cited by this paper
• Threshold Autoregression, Limit Cycles and Cyclical Data

  1980cited by this paper
• Oscillation and chaos in physiological control systems.

  1977cited by this paper

• Monitoring of Caspian Sea-level changes using deep learning-based 3D reconstruction of GRACE signal

  2021cites this paper
• Can Recurrent Neural Networks Predict Inflation in Euro Zone as Good as Professional Forecasters?

  2021cites this paper
• Peramalan Indeks Harga Prulink Rupiah Equity Fund Dengan Metode Exponential Moving Average

  2018cites this paper
• Development of Ship Allocation Models using Marine Logistics Data and its Application to Bulk Carrier Demand Forecasting and Basic Planning Support

  2018cites this paper
• Applying the Kasai to Weather Prediction

  2017influential citation
• A neural network based model for PM2.5 air pollutant forecasting

  2016cites this paper
• Sampling-Based Gradient Regularization for Capturing Long-Term Dependencies in Recurrent Neural Networks

  2016cites this paper
• Norm-preserving Orthogonal Permutation Linear Unit Activation Functions (OPLU)

  2016cites this paper
• Training Dynamic Neural Networks Using the Extended Kalman Filter for Multi-Step-Ahead Predictions

  2015cites this paper
• Direct Method for Training Feed-Forward Neural Networks Using Batch Extended Kalman Filter for Multi-Step-Ahead Predictions

  2013cites this paper