Neural net architectures for temporal sequence processing

91 citations recorded by the source corpus.

How researchers see this paper

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

Autoregressive Convolutional Neural Networks for Asynchronous Time Series (2017, background): “Literature on deep learning for financial time series forecasting is even scarcer though interest in using neural networks for financial predictions is not new (Mozer, 1993; McNelis, 2005).”
Strong systematicity through sensorimotor conceptual grounding: an unsupervised, developmental approach to connectionist sentence processing (2012, background): “Since its development, the SOM has experienced a proliferation of architectural extensions that add the ability to represent temporal sequences of data through a variety of mechanisms (see Mozer 1994, for a review of approaches to temporal representation).”
Deep Feed-Forward Sequential Memory Networks for Speech Synthesis (2018, background): “Neural networks with the tapped delay structure[11, 12] is another popular feed-forward architecture which can efﬁciently model the long temporal contexts.”
Learning Longer Memory in Recurrent Neural Networks (2014, unknown): “This exponential trace memory (as denoted by Mozer (1993)) has been already proposed in the context of simple recurrent networks (Jordan, 1987; Mozer, 1989).”
Sequence learning using the adaptive suffix trie algorithm (2012, background): “However they are not powerful enough to discover relationships that that span long intervals[13].”