Recurrent Neural Networks

By Matteo Bustreo, Carlos Beltrán-González, Vittorio Murino, Filmato Camozzi. 2018

1,728 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Model Architectures

How researchers see this paper

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

In Artificial Intelligence

In Model Architectures

Citations in the corpus

A Review on a Deep Learning Perspective in Brain Cancer Classification (2019, background): “The most common ANN models are extreme learning machines (ELMs) [81], recurrent neural networks (RNN) [82], restricted Boltzmann machine (RBN) [83] etc. ELM is single‐layer feed‐forward neural network (SLFFNN), RNNs apply feedback mechanism in the network connections and RBN is a stochastic neural n”
Is Mamba Effective for Time Series Forecasting? (2024, neutral): “In the context of TSF, it is observed that some variates exhibit a similar pattern of differences, so the generalization potential of the Transformer for sequence data may also take effect on TSF tasks.”
Evaluation of session-based recommendation algorithms (2018, methodology): “…from sequentially ordered data, are a “natural choice” for this problem, and significant advances regarding the prediction accuracy of such algorithms were reported in the recent literature (Hidasi et al. 2016a, b; Tan et al. 2016; Hidasi and Karatzoglou 2017; Devooght and Bersini 2017).”
ChatGPT in Healthcare: A Taxonomy and Systematic Review (2023, background): “In 2017, Vaswani et al. [109] introduced the Transformer model architecture, replacing previously widespread recurrent neural networks (RNN) [76], Long short-term memory networks (LSTM) [45] and Word2Vec [23].”
Quaternion Recurrent Neural Networks (2018, methodology): “The QRNN is an extension of the real-valued (Medsker & Jain, 2001) and complex-valued (Hu & Wang, 2012; Song & Yam, 1998) recurrent neural networks to hypercomplex numbers.”
Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks (2016, methodology): “As illustrated in Figure 3, the function F is then simply a recurrent mapping from RM × R2N → RM corresponding to an implementation by a Feed-Forward Recurrent Neural Network (Medsker and Jain 2001) where the Bt acts as the network’s memory passed from one time step to the next.”
On the Origin of Deep Learning (2017, background): “ Network (RNN) is a class of neural network whose connections of units form a directed cycle; this nature grants its ability to work with temporal data. It has also been discussed in literature like (Grossberg, 2013) and (Lipton et al., 2015). In this paper, we will continue to oer complementary vie”
A critical review of RNN and LSTM variants in hydrological time series predictions (2024, background): “These feedback connections allow RNNs to transmit information from previous events to current processing steps, thus creating a memory of time series occurrences [ 4–6 ].”
Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network (2018, methodology): “Equation 11, Equation 12, and, hence, Equation 14 are nonlinear first-order non-homogeneous DDEs.”
Financial Indices Modelling and Trading utilizing Deep Learning Techniques: The ATHENS SE FTSE/ASE Large Cap Use Case (2018, methodology): “The proposed forecasting model is based on Recurrent Neural Networks composed of LSTM units [15], also known as LSTM networks, which widely used for processing and prediction time series given time lags of unknown size and duration between important events.”
Understanding Deep Learning Techniques for Image Segmentation (2019, methodology): “Various such techniques drew inspiration from popular networks such as AlexNet [104], convolutional autoencoders [141], recurrent neural networks [143], residual networks [78] and so on.”