Results 21 to 30 of about 2,625,571 (293)

Temporal action localization using gated recurrent units

open access: yesThe Visual Computer, 2022
Temporal Action Localization (TAL) task which is to predict the start and end of each action in a video along with the class label of the action has numerous applications in the real world. But due to the complexity of this task, acceptable accuracy rates have not been achieved yet, whereas this is not the case regarding the action recognition task. In
Hassan Keshvari Khojasteh   +2 more
openaire   +3 more sources

Highway Speed Prediction Using Gated Recurrent Unit Neural Networks

open access: yesApplied Sciences, 2021
Movement analytics and mobility insights play a crucial role in urban planning and transportation management. The plethora of mobility data sources, such as GPS trajectories, poses new challenges and opportunities for understanding and predicting ...
Myeong-Hun Jeong   +3 more
doaj   +1 more source

Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units

open access: yesCoRR, 2020
Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the vanilla gates in RNN (e.g., the input gate in LSTM) suffer from the problem of gate undertraining, which can be caused ...
Zhanzhan Cheng   +6 more
openaire   +3 more sources

Short Term Traffic Flow Prediction with Neighbor Selecting Gated Recurrent Unit

open access: yes, 2022
Traffic flow prediction is an important component of a modern intelligent transport system. Building an effective model for short term traffic flow prediction model is challenging. Traffic is spatial temporal in nature.
Andrew Kwok-Fai Lui (16665879)   +2 more
core   +7 more sources

Gated Recurrent Unit Network-Based Short-Term Photovoltaic Forecasting

open access: yesEnergies, 2018
Photovoltaic power has great volatility and intermittency due to environmental factors. Forecasting photovoltaic power is of great significance to ensure the safe and economical operation of distribution network.
Yusen Wang, Wenlong Liao, Yuqing Chang
doaj   +1 more source

Gated Orthogonal Recurrent Units: On Learning to Forget [PDF]

open access: yesNeural Computation, 2019
We present a novel recurrent neural network (RNN)–based model that combines the remembering ability of unitary evolution RNNs with the ability of gated RNNs to effectively forget redundant or irrelevant information in its memory. We achieve this by extending restricted orthogonal evolution RNNs with a gating mechanism similar to gated recurrent unit ...
Li Jing 0001   +6 more
openaire   +6 more sources

Gated recurrent unit neural network (GRU) based on quantile regression (QR) predicts reservoir parameters through well logging data

open access: yesFrontiers in Earth Science, 2023
The prediction of reservoir parameters is the most important part of reservoir evaluation, and porosity is very important among many reservoir parameters.
Zhengjun Yu   +4 more
doaj   +1 more source

Minimum Temperature Forecasting Using Gated Recurrent Unit

open access: yes, 2023
Aim: To forecast the monthly average Minimum Temperature (ºC) in Coimbatore district. Study Design: Gated Recurrent Unit (GRU) has been employed to forecast the Minimum Temperature.
Vasanthi , R.   +4 more
core   +1 more source

Audio Captioning using Gated Recurrent Units

open access: yesCoRR, 2020
Audio captioning is a recently proposed task for automatically generating a textual description of a given audio clip. In this study, a novel deep network architecture with audio embeddings is presented to predict audio captions. Within the aim of extracting audio features in addition to log Mel energies, VGGish audio embedding model is used to explore
Aysegül Özkaya Eren, Mustafa Sert
openaire   +2 more sources

Improving Speech Recognition by Revising Gated Recurrent Units [PDF]

open access: yesInterspeech 2017, 2017
Speech recognition is largely taking advantage of deep learning, showing that substantial benefits can be obtained by modern Recurrent Neural Networks (RNNs). The most popular RNNs are Long Short-Term Memory (LSTMs), which typically reach state-of-the-art performance in many tasks thanks to their ability to learn long-term dependencies and robustness ...
Mirco Ravanelli   +3 more
openaire   +4 more sources

Home - About - Disclaimer - Privacy