A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
How to Construct Deep Recurrent Neural Networks
[article]
2014
arXiv
pre-print
Preserved Fulltext
Other Versions
In this paper, we explore different ways to extend a recurrent neural network (RNN) to a deep RNN. ...
Based on this observation, we propose two novel architectures of a deep RNN which are orthogonal to an earlier attempt of stacking multiple recurrent layers to build a deep RNN (Schmidhuber, 1992; El Hihi ...
We would like to thank NSERC, Compute Canada, and Calcul Québec for providing computational resources. Razvan Pascanu is supported by a DeepMind Fellowship. ...
arXiv:1312.6026v5
fatcat:dkmi2dyijncjlhnqlpay3klnrm
Editorial: Mathematical Fundamentals of Machine Learning
2021
Frontiers in Applied Mathematics and Statistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The first paper, Deductron-A Recurrent Neural Network by Rychlik, studies Recurrent Neural Networks (RNN) by constructing an example of structured data motivated by problems from image-to-text conversion ...
The RNN is constructed by inspection, i.e., its weights are guessed by calling a sequence of carefully designed steps and can be compared to how someone would try to learn by hand. ...
The first paper, Deductron-A Recurrent Neural Network by Rychlik, studies Recurrent Neural Networks (RNN) by constructing an example of structured data motivated by problems from image-to-text conversion ...
doi:10.3389/fams.2021.674785
fatcat:h34x4ngz3rec5ornncndmrlrnu
Data Analysis Deep Learning Research on Spatiotemporal Preposition Construction Network
2022
Wireless Communications and Mobile Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This study is aimed at describing and explaining the functions of CSTPs in constructional networks, aiming to provide clearer semantic information for nonnative language learners. ...
Qualitative analysis includes exploration of cognitive mechanisms, description of semantic networks, misinterpretation, and establishment of lexicographically definition model. ...
analyze how deep learning plays a role in the research of spatiotemporal prepositional construction network. (2) The traditional spatiotemporal preposition construction and the deep learning-based spatiotemporal ...
doi:10.1155/2022/9416747
fatcat:wiroxkotyvfrfidehwfsl4ffmm
Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Neural-symbolic computing has been an active topic of research for many years, reconciling the advantages of robust learning in neural networks and reasoning and interpretability of symbolic representation ...
allowing for the construction of explainable AI systems. ...
Self-transfer with symbolic-knowledge distillation [23] is also useful as it can enhance several types of deep networks such as convolutional neural networks and recurrent neural networks. ...
arXiv:1905.06088v1
fatcat:gm4f3ncukrbevpd7nq5yr75ar4
Research on the air quality prediction model of Wuhai mining area based on deep learning
2021
E3S Web of Conferences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This paper focuses on the corresponding early warning research on air quality in the mining area of Wuhai, and constructs Deep Recurrent Neural Network (DRNN) and Deep Long Short Time Memory Neural Network ...
The model is able to accurately predict the values and trends of various air pollutant concentrations in the mining area of Wuhai. ...
Air quality prediction model based on DRNN
Deep recurrent neural network (DRNN) Deep Recurrent Neural Network is one of the deep learning algorithms, and its main function is to construct a network of ...
doi:10.1051/e3sconf/202130002005
fatcat:bu74uuquzvhuroocnkqlyy42sm
Cascade recurrent neural network for image caption generation
2017
Electronics Letters
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
A new cascade recurrent neural network (CRNN) for image caption generation is proposed. ...
neural network and so on. ...
First, most of them are constructed by the single neural network, which is not flexible to learn deep semantics representation. ...
doi:10.1049/el.2017.3159
fatcat:y5ns3usqhvg4xpibw3h73lq3fi
AIA: Artificial intelligence for art
2018
EVA London 2018
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Recurrent neural network. Reinforcement learning. ...
Today's AI algorithms are limited in how much previous knowledge they are able to keep through each new training phase and how much they can reuse. ...
A recurrent neural network (RNN) is a class of artificial neural network where connections between units form a directed cycle, meaning that Recurrent Neural Network contains feedback connections, connections ...
doi:10.14236/ewic/eva2018.5
dblp:conf/eva/Lisek18
fatcat:wcpjqcrm2zbpvdtnpt63zls2um
Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition
[article]
2015
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Motivated by previous research on constructing deep recurrent neural networks (RNNs), alternative deep LSTM architectures are proposed and empirically evaluated on a large vocabulary conversational telephone ...
To achieve a further performance improvement, in this research, deep extensions on LSTM are investigated considering that deep hierarchical model has turned out to be more efficient than a shallow one. ...
CONCLUSIONS In this paper, we have explored novel approaches to construct long short-term memory (LSTM) based deep recurrent neural networks (RNNs). ...
arXiv:1410.4281v2
fatcat:o7yftzegi5bozghecotv44d64u
Towards Robust Text Classification with Semantics-Aware Recurrent Neural Architecture
2019
Machine Learning and Knowledge Extraction
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Deep neural networks are becoming ubiquitous in text mining and natural language processing, but semantic resources, such as taxonomies and ontologies, are yet to be fully exploited in a deep learning ...
The proposed Semantics-aware Recurrent deep Neural Architecture (SRNA) enables the system to learn simultaneously from the semantic vectors and from the raw text documents. ...
use in a custom deep neural network architecture. ...
doi:10.3390/make1020034
fatcat:o6bjp46cljdj3kng2kxsfvvzei
Study of the impact of the COVID-19 pandemic on international air transportation
2021
Discrete and Continuous Models and Applied Computational Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Architecture for Time Series Forecasting are presented: Recurrent Neural Networks (RNNs), that are the most classical and used architecture for Time Series Forecasting problems; Long Short-Term Memory ...
The author builds time series models of the American Airlines (AAL) stock prices for a selected period using LSTM, GRU, RNN recurrent neural networks models and compare the accuracy forecast results. ...
Basic models of deep neural networks for simulation of financial time series
Basic recurrent neural network The architecture of the proposed basic recurrent neural net (RNN) is as follows. ...
doi:10.22363/2658-4670-2021-29-1-22-35
fatcat:mkbvvodhrfhnndo7ljjepbe55m
Leveraging Product as an Activation Function in Deep Networks
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We demonstrate that WPUNNs can also generalize gated units in recurrent neural networks, yielding results comparable to LSTM networks. ...
Product unit neural networks (PUNNs) are powerful representational models with a strong theoretical basis, but have proven to be difficult to train with gradient-based optimizers. ...
WPUNNs can be used to construct gated units in recurrent neural networks to model time-series data as effectively as LSTM networks. ...
arXiv:1810.08578v1
fatcat:rjk55htxnbbxxdqqrxa6gjzw7q
Intrusion Detection using Recurrent Neural Networks
2020
International Journal for Research in Applied Science and Engineering Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we research how to view a deep learning-dependent interruption location system, and we're going to suggest a deep learning method for interruption attack discovery Use of repetitive neural ...
In this project we are going to analyze the KDD datasets which consists of 44 features based on feature we are going to apply the classification algorithm (Recurrent neural network) which helps in training ...
[6] The Deep Recurrent Neural Networks (DRNNs) model application is introduced in this paper in order to forecast User conduct in networks with Tor. ...
doi:10.22214/ijraset.2020.6335
fatcat:wwkxo63vezhdhirhbkxlrtraum
Emotion Recognition from Variable-Length Speech Segments Using Deep Learning on Spectrograms
2018
Interspeech 2018
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We tried to extract such information from spectrograms and accomplish the emotion recognition task by combining Convolutional Neural Networks (CNNs) with Recurrent Neural Networks (RNNs). ...
In this work, an approach of emotion recognition is proposed for variable-length speech segments by applying deep neutral network to spectrograms directly. ...
In our work, Convolutional Neural Networks (CNNs) are first constructed to learn effectively spatial spectrogram patterns that represent the emotional information; Recurrent Neural Network (RNNs) are then ...
doi:10.21437/interspeech.2018-2228
dblp:conf/interspeech/MaW0XMC18
fatcat:q7hr74umqjahde2dm5x76xtpdm
Neural Networks for Delta Hedging
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this paper, we explore the landscape of Deep Neural Networks(DNN) based hedging systems by testing the hedging capacity of the following neural architectures: Recurrent Neural Networks, Temporal Convolutional ...
Lastly, we construct NNHedge, a deep learning framework that provides seamless pipelines for model development and assessment for the experiments. ...
Finally, to explore how the knowledge of the analytical delta affects
the overall training process we construct a third model, SNN_Pretrained. ...
arXiv:2112.10084v1
fatcat:lo2dd3rkgjdmllbcrmtghh3e6a
Analysis of Enterprise Financial and Economic Impact Based on Background Deep Learning Model under Business Administration
2021
Scientific Programming
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Finally, after the source of uncertainty, the risk prediction and risk management are carried out by constructing decision trees, and these structural models are used to bring comprehensive analysis to ...
How can China play its functions under the new situation after the world economic exchanges are more frequent is an important link to promote the stable development of financial markets. ...
As shown in Figure 6 , the cyclic neural network is equivalent to the upgraded deep learning model construction diagram of the neural network model. ...
doi:10.1155/2021/7178893
fatcat:5gc62crdsjeapc7e6tqvl4g3km
« Previous
Showing results 1 — 15 out of 43,059 results