A convolutional neural network for search term detection

Salehinejad, Hojjat; Barfett, Joseph; Aarabi, Parham; Valaee, Shahrokh; Colak, Errol; Gray, Bruce; Dowdell, Tim

doi:10.1109/pimrc.2017.8292587

Cited by 9 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RNN is a class of artificial neural networks specially designed to process sequential data, such as time series, text, and speech (Salehinejad et al, 2017). Unlike traditional feedforward neural networks (like CNNs), RNNs have connections that form directed cycles, allowing them to maintain internal memory and capture temporal dependencies within the input data.…”

Section: Recurrent Neural Networkmentioning

confidence: 99%

Tomato disease detection with lightweight recurrent and convolutional deep learning models for sustainable and smart agriculture

Le,

Shakiba,

Ardekani

2024

Front. Sustain.

View full text Add to dashboard Cite

show abstract

Section: Recurrent Neural Networkmentioning

confidence: 99%

Tomato disease detection with lightweight recurrent and convolutional deep learning models for sustainable and smart agriculture

Le,

Shakiba,

Ardekani

2024

Front. Sustain.

View full text Add to dashboard Cite

show abstract

“…The LSTM network, a type of recurrent neural network (RNN), employs a cyclic structure that transfers the hidden layer's output back to itself, allowing it to capture temporal features and information from previous time series signals [37]. Proposed by Hochreiter and Schmidhuber [38], LSTM was designed to address the vanishing gradient problem through the use of memory cells [21].…”

Section: Long Short-term Memorymentioning

confidence: 99%

A Methodology for the Prediction of Extreme Precipitation in Complex Terrains: A Case Study of Central Southwest China

Lei,

Yu,

Sun

et al. 2024

Water

View full text Add to dashboard Cite

Against the backdrop of global warming, extreme precipitation events have become more frequent. In complex terrain regions, due to the vulnerability of their ecosystems, extreme precipitation events can lead to significant secondary disasters. Utilizing daily rainfall data from the National Meteorological Information Center of China and statistical analysis, this study explores the spatial and temporal distribution of extreme precipitation in the Central Southwest China (CSC) region. The temporal pattern of extreme precipitation in CSC shows a consistent trend, while the spatial distribution reveals an opposite phase between the northern and southern parts of CSC. Based on this, we propose a new method for constructing extreme precipitation prediction models for complex terrain regions based on physical mechanisms, and take CSC area as a study case. Instead of anonymous feature selection, this method improves the accuracy and stability of the model by studying the impact of sea–air interactions on extreme precipitation and then introducing it into deep learning. It was found that the sea surface temperature (SST) anomaly in the South Indian Ocean affects extreme precipitation in the CSC by influencing uplift, atmospheric instability, and moisture. The SST anomaly also affects the intensity of cross-equatorial airflow, which changes the trajectory of the Pacific–Japan teleconnection wave and impacts extreme precipitation. These findings provide a comprehensive and reliable approach for forecasting extreme precipitation in CSC and are further integrated into the extreme precipitation prediction models.

show abstract

“…A large amount of work has been devoted in the previous years to accelerate RNNs [53]. One of the most commonly applied approaches is to accelerate RNNs by using GPU accelerators [40].…”

Section: Related Workmentioning

confidence: 99%

Wavefront parallelization of recurrent neural networks on multi-core architectures

Sharma

Casas

2020

Proceedings of the 34th ACM International Conference on Supercomputing

View full text Add to dashboard Cite

Recurrent neural networks (RNNs) are widely used for natural language processing, time-series prediction, or text analysis tasks. The internal structure of RNNs inference and training in terms of data or control dependencies across their fundamental numerical kernels complicate the exploitation of model parallelism, which is the reason why just data-parallelism has been traditionally applied to accelerate RNNs. This paper presents W-Par (Wavefront-Parallelization), a comprehensive approach for RNNs inference and training on CPUs that relies on applying model parallelism into RNNs models. We use ne-grained pipeline parallelism in terms of wavefront computations to accelerate multi-layer RNNs running on multi-core CPUs. Wavefront computations have been widely applied in many scienti c computing domains like stencil kernels or dynamic programming. W-Par divides RNNs workloads across di erent parallel tasks by de ning input and output dependencies for each RNN cell. Our experiments considering di erent RNNs models demonstrate that W-Par achieves up to 6.6× speed-up for RNN models inference and training in comparison to current state-of-the-art implementations on modern multi-core CPU architectures. Importantly, W-Par maximizes performance on a wide range of scenarios, including di erent core counts or memory hierarchy con gurations, without requiring any change at the source code level.

show abstract

A convolutional neural network for search term detection

Cited by 9 publications

References 22 publications

Tomato disease detection with lightweight recurrent and convolutional deep learning models for sustainable and smart agriculture

Tomato disease detection with lightweight recurrent and convolutional deep learning models for sustainable and smart agriculture

A Methodology for the Prediction of Extreme Precipitation in Complex Terrains: A Case Study of Central Southwest China

Wavefront parallelization of recurrent neural networks on multi-core architectures

Contact Info

Product

Resources

About