Short-Term Load Forecasting of Natural Gas with Deep Neural Network Regression † [PDF]
Energies, 2018 Deep neural networks are proposed for short-term natural gas load forecasting. Deep learning has proven to be a powerful tool for many classification problems seeing significant use in machine learning fields such as image recognition and speech ...
Gregory D. Merkel +2 more
doaj +3 more sources
The use of adversaries for optimal neural network training [PDF]
EPJ Web of Conferences, 2019 B-decay data from the Belle experiment at the KEKB collider have a substantial background from e+e- -h> qq¯ events. To suppress this we employ deep neural network algorithms. These provide improved signal from background discrimination. However, the deep
Hawthorne-Gonzalvez Anton, Sevior Martin
doaj +4 more sources
A Deep Learning Approach to Predict the Flow Field and Thermal Patterns of Nonencapsulated Phase Change Materials Suspensions in an Enclosure [PDF]
Journal of Applied and Computational Mechanics, 2022 The flow and heat transfer of a novel type of functional phase change nanofluids, nano-encapsulated phase change suspensions, is investigated in the present study using a deep neural networks framework.
Mohammad Edalatifar +2 more
doaj +1 more source
A Survey on Deep Neural Network Pruning: Taxonomy, Comparison, Analysis, and Recommendations [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources.
Hongrong Cheng +2 more
semanticscholar +1 more source
Survey on Backdoor Attacks and Countermeasures in Deep Neural Network [PDF]
Jisuanji kexue yu tansuo, 2023 The neural network backdoor attack aims to implant a hidden backdoor into the deep neural network, so that the infected model behaves normally on benign test samples, but behaves abnormally on poisoned test samples with backdoor triggers.
QIAN Hanwei, SUN Weisong
doaj +1 more source
NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems [PDF]
International Conference on Computer Aided Verification, 2020 This paper presents the Neural Network Verification (NNV) software tool, a set-based verification framework for deep neural networks (DNNs) and learning-enabled cyber-physical systems (CPS). The crux of NNV is a collection of reachability algorithms that
Hoang-Dung Tran +7 more
semanticscholar +1 more source
Deep Neural Networks and An Application in Health Sciences
Van Tıp Dergisi, 2021 INTRODUCTION: Because there is more than one hidden layer between the input and output layers in the neural network algorithm, it is called "Deep Neural Networks". In the study, the Deep Neural Networks algorithm; different input (number of layers, epoch,
Sadi Elasan
doaj +1 more source
Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting [PDF]
International Joint Conference on Artificial Intelligence, 2017 Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect ...
Ting Yu, Haoteng Yin, Zhanxing Zhu
semanticscholar +1 more source
EIE: Efficient Inference Engine on Compressed Deep Neural Network [PDF]
International Symposium on Computer Architecture, 2016 State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources and power budgets.
Song Han +6 more
semanticscholar +1 more source
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network [PDF]
Computer Vision and Pattern Recognition, 2016 Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled
Wenzhe Shi +7 more
semanticscholar +1 more source