Article
Mathematical & Computational Biology
Tianyu Zhan
Summary: This article introduces the application of deep learning in data representation learning, particularly in the field of biomedical research. The article provides guidance on feedforward neural networks and hyperparameter selection, and discusses advanced frameworks and successful applications in the biomedical field.
STATISTICS IN MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Lixia Bai, Hong Li, Weifeng Gao, Jin Xie
Summary: This study proposes a CGA-ELM method based on ELM to simultaneously adjust the structure and parameters of a SLFN. By designing a hybrid coding scheme, the network structure and input parameters can be evolved and the output parameters can be determined using ELM. Experimental results demonstrate that CGA-ELM outperforms CGA and ELM significantly in terms of generalization ability, and has more competitive capacity.
Article
Computer Science, Information Systems
Shahan Yamin Siddiqui, Muhammad Adnan Khan, Sagheer Abbas, Farrukh Khan
Summary: This paper focuses on predicting parking locations using deep extreme learning machine (DELM). The approach enhances familiarity and safety in traffic, reducing parking turbulence. Experimental results demonstrate the effectiveness and accuracy of the proposed DELM method.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Multidisciplinary Sciences
Luis M. C. Oliveira, Vinicius V. Santana, Alirio E. Rodrigues, Ana M. Ribeiro, Idelfonso B. R. Nogueira
Summary: This study developed a framework based on scientific machine learning strategies and utilized transfer learning to predict odor thresholds for chemical substances. Results showed that the transfer learning-based strategy displayed better predictive performance.
Article
Mathematics
Konstantinos Poulinakis, Dimitris Drikakis, Ioannis W. Kokkinakis, Stephen Michael Spottswood
Summary: This study compares machine-learning methods and cubic splines on their ability to handle sparse and noisy training data. The results show that cubic splines provide more precise interpolation than deep neural networks and multivariate adaptive regression splines with very sparse data. However, machine-learning models show robustness to noise and can outperform splines after reaching a threshold of training data. The study aims to provide a general framework for interpolating one-dimensional signals, often obtained from complex scientific simulations or laboratory experiments.
Article
Computer Science, Artificial Intelligence
Ruiyuan Lin, Zhiruo Zhou, Suya You, Raghuveer Rao, C. -C. Jay Kuo
Summary: This work interprets the multilayer perceptron (MLP) neural network from a geometrical viewpoint and proposes a new three-layer feedforward MLP (FF-MLP) architecture for its implementation. Experiments show that the FF-MLP outperforms the traditional backpropagation-based MLP (BP-MLP) in terms of design time, training time, and classification performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Xinyu Gao, Yi Li, Yanqing Qiu, Bangning Mao, Miaogen Chen, Yanlong Meng, Chunliu Zhao, Juan Kang, Yong Guo, Changyu Shen
Summary: The study utilized an optical random scattering system based on LCD and RGB laser source to improve image classification accuracy, achieving excellent classification accuracy of over 94% through ridge classification, suitable for data sets in medical, agricultural, environmental protection, and other fields. The proposed optical scattering system has the advantages of high speed, low power consumption, and miniaturization, making it suitable for edge computing applications.
IEEE PHOTONICS JOURNAL
(2021)
Article
Computer Science, Hardware & Architecture
Fan Wu, Si Hong, Wei Zhao, Xiaoyan Wang, Xun Shao, Xiujun Wang, Xiao Zheng
Summary: This study proposed a pseudo-double hidden layer feedforward neural network model for predicting actual bike-sharing demands. An improved extreme learning machine algorithm was designed to overcome limitations in traditional back-propagation learning process. The performance was verified by comparing with other learning algorithms on a dataset from Streeter Dr bike-sharing station in Chicago.
MOBILE NETWORKS & APPLICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Hector Calvo-Pardo, Tullio Mancini, Jose Olmo
Summary: We propose an optimal architecture for deep neural networks of given size, which optimizes the approximation of linear regions by maximizing the lower bound. The accuracy of the approximation is influenced by the structure of the neural network, including the number, dependence, and hierarchy of nodes within and across layers. Experimental results show that our optimized architecture outperforms cross-validation methods and gridsearch for linear and nonlinear prediction models, as demonstrated on the Boston Housing dataset.
COMPUTERS & OPERATIONS RESEARCH
(2023)
Article
Physics, Multidisciplinary
S. M. Sivalingam, Pushpendra Kumar, V. Govindaraj
Summary: In this paper, a neural network-based approach with an Extreme Learning Machine (ELM) is proposed for solving fractional differential equations. The solution procedure for both linear and nonlinear fractional differential equations is derived, and the convergence and stability of the proposed method are investigated. Numerical solutions for several fractional-order ordinary and partial differential equations are examined, and the impact of changing the number of neurons on solution accuracy is graphically determined.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Meejoung Kim
Summary: This paper introduces the Generalized Extreme Learning Machine (GELM) which incorporates analyzed hyperparameters and a limiting approach for the Moore-Penrose generalized inverse (M-P GI) into the learning process. Experimental results show the advantages of GELM in prediction performance and learning speed.
Article
Mechanics
Suraj Pawar, Omer San, Burak Aksoylu, Adil Rasheed, Trond Kvamsdal
Summary: The study introduces a physics-guided machine learning framework to improve the accuracy of data-driven predictive engines by adding features in intermediate layers to emphasize physical importance. By addressing generalizability concerns, the results suggest that the proposed feature enhancement approach can be effectively used in many scientific machine learning applications.
Article
Computer Science, Artificial Intelligence
Siwar Yahia, Salwa Said, Mourad Zaied
Summary: This paper proposes a new structure based on WNN, deep architecture, and ELM, which improves the classification accuracy in machine learning applications by using a composite wavelet activation function and an ELM auto-encoder with DL structure.
Article
Engineering, Multidisciplinary
Lin Xu, Xiangyong Cao, Jing Yao, Zheng Yan
Summary: In this paper, we propose an Orthogonal Super Greedy learning (OSGL) method for hidden neurons selection in feedforward neural networks. The method addresses the issue of generation performance and computational complexity being affected by irrelevant hidden variables. Theoretical analyses and empirical results demonstrate that the proposed method can achieve optimal learning rate and produce excellent generalization performance with a sparse and compact feature representation.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Geosciences, Multidisciplinary
Raymond Sellevold, Miren Vizcaino
Summary: This study combines artificial neural networks with CESM2 and RCM simulations to establish relationships between global climate model output and Greenland ice sheet melt. The models estimate an increasing trend in Greenland ice sheet melt in the future, with climate model sensitivity being the primary source of uncertainty throughout the 21st century.
GEOPHYSICAL RESEARCH LETTERS
(2021)