Recurrent neural networks and robust time series prediction

By Jerome T. Connor, R. Martin, Les E. Atlas. 1994

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

Deep learning in neural networks: An overview (2014, methodology): “There have been numerous applications of GMDH-style nets, e.g. Farlow (1984), Ikeda, Ochiai, and Sawaragi (1976), Ivakhnenko (1995), Kondo (1998), Kondo and Ueno (2008), Kordík, Náplava, Snorek, and Genyk-Berezovskyj (2003), Madala and Ivakhnenko (1994) and Witczak, Korbicz, Mrugalski, and Patton…”
Neural network ensemble operators for time series forecasting (2014, background): “Their attractive properties have led to the rise of several types of NNs and applications in the literature (for examples, see Connor et al., 1994; Zhang et al., 1998; Efendigil et al., 2009; Khashei and Bijari, 2010).”
Deep Learning Based Forecasting of Critical Infrastructure Data (2017, unknown): “Beyond accuracy related measures, the quality of the forecasting method is essential, meaning for each data point there is a reliable estimation of the next value [3, 7, 14].”
Mercury: Metro density prediction with recurrent neural network on streaming CDR data (2016, background): “Stochastic Models [5], Artificial Neural Networks (ANNs) [2], [6] Support Vector Machines (SVM) [15], and Gaussian Process [16], [13] are four schools of mod-”
Forecasting Exchange Rates: A Robust Regression Approach (2007, background): “small samples. However, it was shown by Connor and Martin (1994) and, Connor”
Avoiding Pitfalls in Neural Network Research (2007, background): “[30] demonstrate that recurrent neural networks are a special case of nonlinear autoregres-”
A Survey on Machine-Learning Techniques in Cognitive Radios (2013, methodology): “…prediction method was done by exploiting the cyclostationary signal features to construct a RF multivariate time series that contain more information than the univariate time series [155], in contrast to most of the modeling methodologies which focus on the univariate time series prediction [156].”
NARMAX time series model prediction: feedforward and recurrent fuzzy neural network approaches (2005, methodology): “Relaxation networks start from a given state and settle to a fixed point, typically denoting a class [5].”
Prediction for the spread of COVID-19 in India and effectiveness of preventive measures (2020, unknown): “To remove that shortcomings, Hochreiter and Schmidhuber designed long short-term memory RNN structure in 1997 (Hochreiter and Schmidhuber, 1997) to deal with a long-term dependency with themultiplicative gates that regulate the information flow andmemory cells in the recurrent hidden layer.”
Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications (2000, background): “Connor et al. (1994) have shown that feedforward neural networks are a special case of non-linear autoregressive (NAR) models and that recurrent neural networks are a special case of non-linear autoregressive moving average (NARMA) models.”
Intelligent Predictive Decision Support System for Condition-Based Maintenance (2001, methodology): “Recent work on forecasting nonlinear, non-stationary and non-Gaussian-type time series also indicates that recurrent neural networks (RNNs) have a better forecasting performance than other methods [8,40, 41 ].”
Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers (2020, result): “This distinguishes our work from studies of recurrent ANN architectures [11, 54, 62] as the PDE-solver can introduce significant non-linearities in-between evaluations of the ANN.”
EOF Calculations and Data Filling from Incomplete Oceanographic Datasets (2003, background): “New sentence at P9 L3 to L4: The final DNN architecture, as shown in Figure 4, contains three LSTM layers, followed by two dense layers with dropout, a convolutional layer, and a final output dense layer Reviewer Comment 3.16 —”