FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4365504037> ?p ?o ?g. }

• W4365504037 abstract "Abstract Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for many applications dismissing the use of DL. Having sufficient data is the first step toward any successful and trustworthy DL application. This paper presents a holistic survey on state-of-the-art techniques to deal with training DL models to overcome three challenges including small, imbalanced datasets, and lack of generalization. This survey starts by listing the learning techniques. Next, the types of DL architectures are introduced. After that, state-of-the-art solutions to address the issue of lack of training data are listed, such as Transfer Learning (TL), Self-Supervised Learning (SSL), Generative Adversarial Networks (GANs), Model Architecture (MA), Physics-Informed Neural Network (PINN), and Deep Synthetic Minority Oversampling Technique (DeepSMOTE). Then, these solutions were followed by some related tips about data acquisition needed prior to training purposes, as well as recommendations for ensuring the trustworthiness of the training dataset. The survey ends with a list of applications that suffer from data scarcity, several alternatives are proposed in order to generate more data in each application including Electromagnetic Imaging (EMI), Civil Structural Health Monitoring, Medical imaging, Meteorology, Wireless Communications, Fluid Mechanics, Microelectromechanical system, and Cybersecurity. To the best of the authors’ knowledge, this is the first review that offers a comprehensive overview on strategies to tackle data scarcity in DL." @default.
• W4365504037 created "2023-04-15" @default.
• W4365504037 creator A5004901591 @default.
• W4365504037 creator A5010765865 @default.
• W4365504037 creator A5012505948 @default.
• W4365504037 creator A5017903283 @default.
• W4365504037 creator A5021489599 @default.
• W4365504037 creator A5029299521 @default.
• W4365504037 creator A5031304262 @default.
• W4365504037 creator A5034339111 @default.
• W4365504037 creator A5035513892 @default.
• W4365504037 creator A5052319607 @default.
• W4365504037 creator A5059266881 @default.
• W4365504037 creator A5062462649 @default.
• W4365504037 creator A5066206447 @default.
• W4365504037 creator A5066987395 @default.
• W4365504037 creator A5084844724 @default.
• W4365504037 creator A5085799439 @default.
• W4365504037 creator A5088650299 @default.
• W4365504037 creator A5090966997 @default.
• W4365504037 date "2023-04-14" @default.
• W4365504037 modified "2023-10-12" @default.
• W4365504037 title "A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications" @default.
• W4365504037 cites W159393988 @default.
• W4365504037 cites W1630571149 @default.
• W4365504037 cites W1806891645 @default.
• W4365504037 cites W1976986752 @default.
• W4365504037 cites W1978201146 @default.
• W4365504037 cites W1978370894 @default.
• W4365504037 cites W2007339694 @default.
• W4365504037 cites W2011878020 @default.
• W4365504037 cites W2021688474 @default.
• W4365504037 cites W2025411198 @default.
• W4365504037 cites W2066215243 @default.
• W4365504037 cites W2067148378 @default.
• W4365504037 cites W2106195076 @default.
• W4365504037 cites W2115305326 @default.
• W4365504037 cites W2115651492 @default.
• W4365504037 cites W2115733720 @default.
• W4365504037 cites W2129018774 @default.
• W4365504037 cites W2136655611 @default.
• W4365504037 cites W2141736632 @default.
• W4365504037 cites W2148143831 @default.
• W4365504037 cites W2157189144 @default.
• W4365504037 cites W2339754110 @default.
• W4365504037 cites W2530225882 @default.
• W4365504037 cites W2557449848 @default.
• W4365504037 cites W2563194670 @default.
• W4365504037 cites W2566832195 @default.
• W4365504037 cites W2587706859 @default.
• W4365504037 cites W2592232824 @default.
• W4365504037 cites W2623550831 @default.
• W4365504037 cites W2729018917 @default.
• W4365504037 cites W2785232201 @default.
• W4365504037 cites W2786070938 @default.
• W4365504037 cites W2786585376 @default.
• W4365504037 cites W2790690116 @default.
• W4365504037 cites W2791957585 @default.
• W4365504037 cites W2796200341 @default.
• W4365504037 cites W2796355903 @default.
• W4365504037 cites W2798729263 @default.
• W4365504037 cites W2798874329 @default.
• W4365504037 cites W2800287223 @default.
• W4365504037 cites W2802300457 @default.
• W4365504037 cites W2803122122 @default.
• W4365504037 cites W2803465596 @default.
• W4365504037 cites W2883074505 @default.
• W4365504037 cites W2883102461 @default.
• W4365504037 cites W2891158090 @default.
• W4365504037 cites W2894787842 @default.
• W4365504037 cites W2897095370 @default.
• W4365504037 cites W2898280479 @default.
• W4365504037 cites W2899128648 @default.
• W4365504037 cites W2899283552 @default.
• W4365504037 cites W2900066992 @default.
• W4365504037 cites W2900369848 @default.
• W4365504037 cites W2900529838 @default.
• W4365504037 cites W2904255355 @default.
• W4365504037 cites W2906031885 @default.
• W4365504037 cites W2908454557 @default.
• W4365504037 cites W2908541468 @default.
• W4365504037 cites W2909327627 @default.
• W4365504037 cites W2911106207 @default.
• W4365504037 cites W2913340405 @default.
• W4365504037 cites W2919358988 @default.
• W4365504037 cites W2921948732 @default.
• W4365504037 cites W2929050222 @default.
• W4365504037 cites W2942231644 @default.
• W4365504037 cites W2943766732 @default.
• W4365504037 cites W2945976633 @default.
• W4365504037 cites W2946724317 @default.
• W4365504037 cites W2948704044 @default.
• W4365504037 cites W2949843150 @default.
• W4365504037 cites W2950087183 @default.
• W4365504037 cites W2951107941 @default.
• W4365504037 cites W2953958347 @default.
• W4365504037 cites W2954074628 @default.
• W4365504037 cites W2954154461 @default.
• W4365504037 cites W2955109214 @default.
• W4365504037 cites W2957568672 @default.

• next