A Technical Note on the Architectural Effects on Maximum Dependency Lengths of Recurrent Neural Networks
Neural and Evolutionary Computing
2024-08-23 v1
Abstract
This work proposes a methodology for determining the maximum dependency length of a recurrent neural network (RNN), and then studies the effects of architectural changes, including the number and neuron count of layers, on the maximum dependency lengths of traditional RNN, gated recurrent unit (GRU), and long-short term memory (LSTM) models.
Cite
@article{arxiv.2408.11946,
title = {A Technical Note on the Architectural Effects on Maximum Dependency Lengths of Recurrent Neural Networks},
author = {Jonathan S. Kent and Michael M. Murray},
journal= {arXiv preprint arXiv:2408.11946},
year = {2024}
}
Comments
13 pages, 12 figures