An adaptive mechanism to achieve learning rate dynamically
Sign Up to like & getrecommendations! Published in 2018 at "Neural Computing and Applications"
DOI: 10.1007/s00521-018-3495-0
Abstract: Gradient descent is prevalent for large-scale optimization problems in machine learning; especially it nowadays plays a major role in computing and correcting the connection strength of neural networks in deep learning. However, many gradient-based optimization… read more here.
Keywords: mechanism; exponential decay; adaptive mechanism; rate ... See more keywords
Robust optimization of SVM hyper-parameters for spillway type selection
Sign Up to like & getrecommendations! Published in 2021 at "Ain Shams Engineering Journal"
DOI: 10.1016/j.asej.2020.10.022
Abstract: Abstract Spillways, which play a vital role in dams, can be built in various types. Although several studies have been conducted on hydraulic calculations of spillways, studies on type selection that require heuristics knowledge were… read more here.
Keywords: optimization; type selection; svm; hyper parameters ... See more keywords
Selecting Hyper-Parameters of Gaussian Process Regression Based on Non-Inertial Particle Swarm Optimization in Internet of Things
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Access"
DOI: 10.1109/access.2019.2913757
Abstract: Gaussian process regression (GPR) is frequently used for uncertain measurement and prediction of nonstationary time series in the Internet of Things data, nevertheless, the generalization and regression efficacy of GPR are directly impacted by its… read more here.
Keywords: regression; hyper parameters; non inertial; process regression ... See more keywords
Model Capacity Vulnerability in Hyper-Parameters Estimation
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Access"
DOI: 10.1109/access.2020.2969276
Abstract: Machine learning models are vulnerable to a variety of data perturbation. Recent research mainly focuses on the vulnerability of model training and proposes various model-oriented defense methods to achieve robust machine learning. However, most of… read more here.
Keywords: model; vulnerability; model capacity; hyper parameters ... See more keywords
Deep Learning With Adaptive Hyper-Parameters for Low-Dose CT Image Reconstruction
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Computational Imaging"
DOI: 10.1109/tci.2021.3093003
Abstract: Low-dose CT (LDCT) imaging is preferred in many applications to reduce the object's exposure to X-ray radiation. In recent years, one promising approach to image reconstruction in LDCT is the so-called optimization-unrolling-based deep learning approach,… read more here.
Keywords: image reconstruction; deep learning; image; hyper parameters ... See more keywords
Effect of hyper-parameters on the performance of ConvLSTM based deep neural network in crop classification
Sign Up to like & getrecommendations! Published in 2023 at "PLOS ONE"
DOI: 10.1371/journal.pone.0275653
Abstract: Deep learning based data driven methods with multi-sensors spectro-temporal data are widely used for pattern identification and land-cover classification in remote sensing domain. However, adjusting the right tuning for the deep learning models is extremely… read more here.
Keywords: classification; convlstm; deep learning; model ... See more keywords
Analyzing the Influence of Hyper-parameters and Regularizers of Topic Modeling in Terms of Renyi Entropy
Sign Up to like & getrecommendations! Published in 2020 at "Entropy"
DOI: 10.3390/e22040394
Abstract: Topic modeling is a popular technique for clustering large collections of text documents. A variety of different types of regularization is implemented in topic modeling. In this paper, we propose a novel approach for analyzing… read more here.
Keywords: renyi entropy; entropy; topic modeling; hyper parameters ... See more keywords
Research on Hyper-Parameter Optimization of Activity Recognition Algorithm Based on Improved Cuckoo Search
Sign Up to like & getrecommendations! Published in 2022 at "Entropy"
DOI: 10.3390/e24060845
Abstract: Activity recognition methods often include some hyper-parameters based on experience, which greatly affects their effectiveness in activity recognition. However, the existing hyper-parameter optimization algorithms are mostly for continuous hyper-parameters, and rarely for the optimization of… read more here.
Keywords: hyper parameters; algorithm; activity recognition;