Results 71 to 80 of about 216,131 (169)

Sorghum crops classification and segmentation using shifted window transformer neural network and localization based on (YOLO)v9-path aggregation network

Frontiers in Plant Science
IntroductionThe world’s population has been increasing continuously, and this requires prompt action to ensure food security. One of the top five cereals produced worldwide, sorghum, is a staple of the diets of many developing nations.
Javaria Amin, Rida Zahra, Alena Maryum, Amber Sarwar, Amad Zafar, Seong-Han Kim   +5 more
doaj   +1 more source

Towards Sustainable Construction Materials: A Comparative Study of Prediction Models for Green Concrete with Metakaolin

Buildings, 2022
Cement-based materials are widely used in transportation, construction, national defense, and other fields, due to their excellent properties. High performance, low energy consumption, and environmental protection are essential directions for the ...
Jiandong Huang, Mengmeng Zhou, Hongwei Yuan, Mohanad Muayad Sabri Sabri, Xiang Li   +4 more
doaj   +1 more source

EDEN: Evolutionary Deep Networks for Efficient Machine Learning

, 2017
Deep neural networks continue to show improved performance with increasing depth, an encouraging trend that implies an explosion in the possible permutations of network architectures and hyperparameters for which there is little intuitive guidance.
Bassett, Bruce A., Dufourq, Emmanuel
core   +1 more source

Optimization of Electromyography (EMG) Signal Parameters for Assistive Device Control Using a Convolutional Neural Network (CNN)

Communications in Science and Technology
Facial Electromyography (EMG) signals offer a promising modality for intuitive human-machine interfaces (HMIs). The development of robust control systems, however, remains challenging in view of the inherent complexity, noise susceptibility, and ...
Irfan Wahyu Ramadhan, Sisdarmanto Adinandra   +1 more
doaj   +1 more source

Recommending Learning Algorithms and Their Associated Hyperparameters [PDF]

, 2014
The success of machine learning on a given task dependson, among other things, which learning algorithm is selected and its associated hyperparameters. Selecting an appropriate learning algorithm and setting its hyperparameters for a given data set can ...
Giraud-Carrier, Christophe, Martinez, Tony, Mitchell, Logan, Smith, Michael R.   +3 more
core  

Integrated Hyperparameter Optimization with Dimensionality Reduction and Clustering for Radiomics: A Bootstrapped Approach

Multimodal Technologies and Interaction
Radiomics involves extracting quantitative features from medical images, resulting in high-dimensional data. Unsupervised clustering has been used to discover patterns in radiomic features, potentially yielding hidden biological insights.
S. J. Pawan, Matthew Muellner, Xiaomeng Lei, Mihir Desai, Bino Varghese, Vinay Duddalwar, Steven Y. Cen   +6 more
doaj   +1 more source

An approximate empirical Bayesian method for large-scale linear-Gaussian inverse problems

, 2018
We study Bayesian inference methods for solving linear inverse problems, focusing on hierarchical formulations where the prior or the likelihood function depend on unspecified hyperparameters.
Bardsley J M, Calvetti D, Calvetti D, Casella G, Cui T, Fornberg B, Jinglai Li, Johnson K A, Kaipio J, Press W H, Qingping Zhou, Radon J, Rao C R, Rasmussen C E, Stein M L, Wenqing Liu, Yao Z, Youssef M Marzouk   +17 more
core   +1 more source

Bio-Inspired Hyperparameter Tuning of Federated Learning for Student Activity Recognition in Online Exam Environment

AI
Nowadays, online examination (exam in short) platforms are becoming more popular, demanding strong security measures for digital learning environments. This includes addressing key challenges such as head pose detection and estimation, which are integral
Ramu Shankarappa, Nandini Prasad, Ram Mohana Reddy Guddeti, Biju R. Mohan   +3 more
doaj   +1 more source

Efficient Optimization of Echo State Networks for Time Series Datasets

, 2019
Echo State Networks (ESNs) are recurrent neural networks that only train their output layer, thereby precluding the need to backpropagate gradients through time, which leads to significant computational gains.
Gianniotis, Nikos, Maat, Jacob Reinier, Protopapas, Pavlos   +2 more
core   +1 more source

Understanding and Comparing Scalable Gaussian Process Regression for Big Data

, 2018
As a non-parametric Bayesian model which produces informative predictive distribution, Gaussian process (GP) has been widely used in various fields, like regression, classification and optimization.
Cai, Jianfei, Liu, Haitao, Ong, Yew-Soon, Wang, Yi   +3 more
core   +1 more source