Reprint

Deep Learning Architecture and Applications

Edited by
October 2023
406 pages
  • ISBN978-3-0365-8830-8 (Hardback)
  • ISBN978-3-0365-8831-5 (PDF)

This is a Reprint of the Special Issue Deep Learning Architecture and Applications that was published in

Computer Science & Mathematics
Summary

As one of the fastest-growing topics in machine learning, deep learning algorithms have achieved unprecedented success in recent years. Novel paradigms (such as contrastive learning and few-shot learning) in deep learning and rising neural network architectures (e.g., transformer and masked autoencoder) are dramatically changing the field of data-driven algorithms. More importantly, deep learning models are redefining the next generation of industrial applications spanning image recognition, speech processing, language translation, healthcare, and other sciences. For example, recent advances in deep representation learning are allowing us to learn about protein 3D structures, which sheds new light on fundamental medicine and biology along with potentially bringing in billions of dollars (e.g., in the pharmaceutical market). This collection gathers the advanced studies of novel deep learning algorithms/frameworks and their applications in real-world scenarios. The topics cover, but are not limited to, supervised learning, explainable deep learning, finance, healthcare, and sciences.

Format
  • Hardback
License and Copyright
© 2022 by the authors; CC BY-NC-ND license
Keywords
Convolutional Neural Network (CNN); pooling; deep learning; computer vision; image analysis; benchmark; lithium-ion battery; prognostics; long short-term memory; ARIMA; reinforcement learning; generative adversarial networks; deep-learning; crop/weed classification; transfer learning; feature extraction; deep learning; computer vision; natural language processing; image-text matching; cheapfakes; misinformation; transformer encoder; RoGPT2; control tokens; summarization; text generation; human evaluation; tricalcium silicate; analytical model; ion activity; dissolution kinetics; deep forest; subsurface fluid flow; Fourier neural operator; small-shape data; finite element method; convolutional neural network; sensitivity analysis; source code comments; classification; machine learning techniques; ANN flow law; constitutive behavior; radial return algorithm; numerical implementation; VUHARD; GrC15; Abaqus Explicit; defect detection; surface defect detection; defect detection for X-ray images; defect recognition; deep learning; photoacoustic imaging; image processing; computer vision; simulation; reconstruction; deep learning; residual echo suppression; acoustic echo cancellation; deep-learning; speech enhancement; graph neural network; variational autoencoder; pooling; nearest neighbours; acute myeloid leukemia; risk factors; average treatment effect; uplift modelling; machine learning; benzene; ANOVA; Shapley values; self-explaining neural networks; generalised additive models; interpretability; Siamese networks; synthetic data; cyclic learning; unsupervised learning; deep learning; data augmentation; single cell cultivation; bioimage analysis; deep learning; machine learning; finite element simulation; plausibility checks; convolutional neural networks; machine learning; storm surge; hurricane; forecasting; CNN; LSTM; physics informed neural network; dynamic force identification; deep learning; duffing’s equation; spring mass damper system; non-linear oscillators; massive MIMO; hybrid beamforming; compressive measurement matrix; long short-term memory network; convolutional neural network; capsule network; routing algorithm