Recurrent neural networks

By Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, Domonkos Tikk. 2013

997 citations recorded by the source corpus.

This chapter presents an introduction to recurrent neural networks for readers familiar with artificial neural networks in general, and multi-layer perceptrons trained with gradient descent algorithms (back-propagation) in particular. A recurrent neural network (RNN) is an artificial neural network with internal loops. These internal loops induce recursive dynamics in the networks and thus introduce delayed activation dependencies across the processing elements (PEs) in the network.

Subfields: Artificial Intelligence

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

Citations in the corpus

Real-time prediction of online shoppers’ purchasing intention using multilayer perceptron and LSTM recurrent neural networks (2018, background): “Although recently a few studies have used RNN to process e-commerce data, these studies focused on session-based recommender systems in which a recommendation is produced after each consecutive click of the user [21].”
ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation (2020, methodology): “Various recurrent neural networks [10, 11] and attention mechanisms [16, 18, 20] have been proposed for φ, and the common choices for the output layer ω is fully-connect layers[11] or bi-linear decoders [16, 18].”
A Meta-Learning Perspective on Cold-Start Recommendations for Items (2017, background): “[9, 10] propose RNN architecture for a similar problem, namely that of recommending items during short-lived web sessions.”
S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization (2020, methodology): “ predict the next item given the last interaction of a user. A series of works follow this line and extend it for high-order MCs [4, 8, 24]. With the development of the neural networks, Hidasi et al. [3] firstly introduced Gated Recurrent Units (GRU) to the session-based recommendation and a surge o”
Modelling Contextual Information in Session-Aware Recommender Systems with Neural Networks (2016, background): “To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee.”
Towards Universal Sequence Representation Learning for Recommender Systems (2022, methodology): “Despite the progress, most of existing SRL methods for recommendation rely on explicit item IDs for developing the sequence models [6, 10].”
A critical review of RNN and LSTM variants in hydrological time series predictions (2024, background): “The vanishing gradient problem of RNNs delays the ability to capture long-term dependencies, which results in low accuracy in long-term predictions [ 5 ].”
Towards the Development of Realistic Botnet Dataset in the Internet of Things for Network Forensic Analytics: Bot-IoT Dataset (2018, background): “• RNN: incorporates a form of memory in its structure [64].”
Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning (2018, methodology): “Here we leverage GRU rather than Long Short-Term Memory (LSTM) because that GRU outperforms LSTM for capturing users’ sequential behaviors in recommendation task [8].”
Sampling-bias-corrected neural modeling for large corpus item recommendations (2019, methodology): “As a result, unlike training MLP models where negatives are sampled from a fxed corpus, we consider only using in-batch items [22] as negatives for all queries from the same batch.”