Deep learning modelling techniques: current progress, applications, advantages, and challenges

Abstract

Deep learning (DL) is revolutionizing evidence-based decision-making techniques that can be applied across various sectors. Specifically, it possesses the ability to utilize two or more levels of non-linear feature transformation of the given data via representation learning in order to overcome limitations posed by large datasets. As a multidisciplinary field that is still in its nascent phase, articles that survey DL architectures encompassing the full scope of the field are rather limited. Thus, this paper comprehensively reviews the state-of-art DL modelling techniques and provides insights into their advantages and challenges. It was found that many of the models exhibit a highly domain-specific efficiency and could be trained by two or more methods. However, training DL models can be very time-consuming, expensive, and requires huge samples for better accuracy. Since DL is also susceptible to deception and misclassification and tends to get stuck on local minima, improved optimization of parameters is required to create more robust models. Regardless, DL has already been leading to groundbreaking results in the healthcare, education, security, commercial, industrial, as well as government sectors. Some models, like the convolutional neural network (CNN), generative adversarial networks (GAN), recurrent neural network (RNN), recursive neural networks, and autoencoders, are frequently used, while the potential of other models remains widely unexplored. Pertinently, hybrid conventional DL architectures have the capacity to overcome the challenges experienced by conventional models. Considering that capsule architectures may dominate future DL models, this work aimed to compile information for stakeholders involved in the development and use of DL models in the contemporary world.

Multidirectional Analysis of Curvelet Against Skin Cancer

“…The input patterns are changed by the feature extraction module to be represented by lowdimensional vectors that are reasonably invariant to changes and distortions of the input patterns that do not alter its essence and that are simple to match or compare [65].…”

Identification and reconstruction of anomalous data in dam monitoring considering temporal correlation

“…Dam monitoring data often contains numerous nonlinear relationships, and traditional mathematical reconstruction methods necessitate the construction of suitable mathematical models to explore these relationships in order to reconstruct abnormal data accurately. DMDRN, on the other hand, is an enhanced network based on GAN and serves as a deep learning framework that can better explore the nonlinear relationships [33][34][35] in dam monitoring data and generate precise reconstruction values. Additionally, when it comes to processing large-scale dam monitoring data, traditional statistical methods are time-consuming and inefficient, whereas DMDRN (as a deep learning framework) is more advantageous [33].…”

“…DMDRN, on the other hand, is an enhanced network based on GAN and serves as a deep learning framework that can better explore the nonlinear relationships [33][34][35] in dam monitoring data and generate precise reconstruction values. Additionally, when it comes to processing large-scale dam monitoring data, traditional statistical methods are time-consuming and inefficient, whereas DMDRN (as a deep learning framework) is more advantageous [33].…”

Enhancing glucose classification in continuous flow hydrothermal biomass liquefaction streams through generative AI and IR spectroscopy

“…This advantage translates into improved performance, enabling the models to generate more realistic samples and achieve greater accuracy in distinguishing between real and fake samples. 38 By increasing the dimension of the nodes in discriminator, it was expected that the network would extract more information from the generator. 39 Combining the aforementioned generator and discriminator models results in the construction of the GAN model.…”