Recurrent Networks and NARMA Modeling

By Jerome T. Connor, Les E. Atlas, Ft-Lo, D. Martin. 1991

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series (2017, methodology): “nts an unknown smooth function and " t is a white noise error term. For a detailed derivation and non-linear approximation of feedforward networks and fully interconnected RNNs to g, we refer to Connor et al. (1992, 1994). Hence, an unrolled RNN in time approximates the statistical ARMA framewo”
A Multi-Horizon Quantile Recurrent Forecaster (2017, methodology): “Historically, RNN ﬁts into the Nonlinear Autoregressive Moving Average framework (Connor et al, 1992).”
Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability (2001, background): “6.1 Perspective 91 6.2 Introduction 91 6.3 Overview 92 6.4 Neural Networks and Polynomial Filters 92 6.5 Neural Networks and Nonlinear Adaptive Filters 95 6.6 Training Algorithms for Recurrent Neural Networks 101 6.7 Learning Strategies for a Neural Predictor/Identifier 101 6.7.1 Learning Strategies”
Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks (2017, methodology): “ries in the past to predict the unknown time series in a look-ahead horizon – the large the horizon, the harder the problem. Efforts in this direction range from the early work using naive RNN models [7] and the hybrid models [16, 33, 34] combining the use of ARIMA [3] and 2 Multilayer Perceptron (M”
Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach (2017, methodology): “For a detailed derivation and non-linear approximation of feedforward networks and fully interconnected RNNs to g, we refer to Connor et al. (1992, 1994).”
Position-Based Content Attention for Time Series Forecasting with Sequence-to-Sequence RNNs (2017, background): “Early work [17] has shown that RNNs (a) are a type of nonlinear autoregressive moving average (NARMA) model and (b) outperform feed-forward networks and various types of linear statistical models on time series.”
Learning long-term dependencies in NARX recurrent neural networks (1996, background): “It has been demonstrated that they are well suited for modeling nonlinear systems such as heat exchangers [3], waste water treatment plants [34, 35], catalytic reforming systems in a petroleum re nery [35], nonlinear oscillations associated with multi{legged locomotion in biological systems [36], ti”