Neural Networks for Time Series Processing

By Georg Dorffner. 1996

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): “Each RNN is trained for a while in unsupervised fashion to predict its next input (e.g., Connor, Martin, & Atlas, 1994; Dorffner, 1996).”
The use of NARX neural networks to predict chaotic time series (2008, background): “a function computing the cost resulting from an incorrect prediction of y(t+D))[2].”
Neural Networks and Deep Learning (2018, unknown): “The vast majority of work on recurrent networks has been on symbolic data, although there is also some work on real-valued time series [80, 101, 559].”
Wave physics as an analog recurrent neural network (2019, background): “[12] Georg Dorffner, “Neural Networks for Time Series Processing,” Neural Network World 6, 447–468 (1996).”
Univariate modelling of monthly maximum temperature time series over northeast India: neural network versus Yule–Walker equation based approach (2011, background): “…= p∑ i=1 φiz(t − i)+ ∈ (t) (10) In Equation (10), a linear function F L can be introduced, in which case the equivalent form of Equation (10) would be (Dorffner, 1996): z(t) = F L(z(t − 1), z(t − 2), . . . , z(t − p))+ ∈ (t) (11) Replacing L by an ANN model leads to the autoregressive neural…”
Generative Adversarial Networks in Time Series: A Systematic Literature Review (2022, background): “As Dorfner states, a time series can be viewed, from a practical perspective, as a value sampled at discrete steps in time [25].”
Improved supply chain management based on hybrid demand forecasts (2007, methodology): “There are many publications comparing ARIMA and neural networks, both theoretically [6,20] and empirically [7,12].”
When Are Tree Structures Necessary for Deep Learning of Representations? (2015, methodology): “Recurrent models (also referred to as sequence models) deal successfully with time-series data (Pearlmutter, 1989; Dorffner, 1996) like speech (Robinson et al.”
Time Series Prediction and Neural Networks (2001, unknown): “As noted in [4] this technique can be seen as an extension of auto-regressive time series modelling, in which the function ƒ is assumed to be a linear combination of a fixed number of previous series values.”
Application of machine learning techniques for supply chain demand forecasting (2008, background): “Inaccurate information too would lead to demand distortion, as was the case reported in a study of the telecom industry demand chain where some partners were double forecasting and ration gaming (Heikkilä, 2002), despite the fact that there was a collaborative system in place and a push for the…”
Time Series Prediction with the Self-Organizing Map: A Review (2007, background): “To our knowledge, this paper is the first of its type, since former surveys on neural networks for time series prediction (see, for example, [44, 18, 64, 13]) only report just a few SOM-based applications (or even none at all!).”