Hoang-Thang Ta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hoang-Thang Ta has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Abu Bakar Siddiqur Rahman
College of Information Science and Technology Centro de Intestigacion en Computacion (CIC) University of Nebraska Omaha Nebraska USA
4 shared publications - Alexander Gelbukh
CIC, Instituto Politécnico Nacional
4 shared publications - Lotfollah Najjar
Dalat University University of Nebraska at Omaha University of Nebraska at Omaha Instituto Politécnico Nacional (IPN) Mexico
4 shared publications - Thai Duy Quy
Department of Information Technology Dalat University Lam Dong Vietnam
3 shared publications - Ali Saffet Gonul
SoCAT Lab, Department of Psychiatry, School of Medicine, Ege University, İzmir, Türkiye
2 shared publications - Azad Azadmanesh
College of Information Science and Technology, University of Nebraska Omaha, USA
2 shared publications
Latest Publications
- 8 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 706
SechKAN: Kolmogorov–Arnold networks with hyperbolic secant functions
- 8 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 706
SechKAN: Kolmogorov–Arnold networks with hyperbolic secant functions
- 2 September 2026
- Published by Springer Nature
- p. 467-477
Self-training from Self-memory in Data-to-Text Generation
- 2 September 2026
- Published by Springer Nature
- p. 467-477
Self-training from Self-memory in Data-to-Text Generation
- Open Access
- 23 June 2026
- Published by Elsevier in SSRN Electronic Journal
SechKAN: Kolmogorov–Arnold Networks with Hyperbolic Secant Functions
SechKAN: Kolmogorov–Arnold Networks with Hyperbolic Secant FunctionsaIn recent years, Kolmogorov–Arnold Networks (KANs) have attracted increasing attention due to their effectiveness in machine learning and scientific computing tasks, offering a new paradigm for neural network design. In this paper, we present SechKAN, a KAN architecture based on hyperbolic secant (sech) functions. The hyperbolic secant basis is used for its smooth bell-shaped form, localized responses, and stable gradients. We employ 1D linear transformations to reduce the number of parameters, allowing SechKAN to remain comparable to multilayer perceptrons (MLPs) in model size. Experimental results indicate the effectiveness of SechKAN in function fitting, PDE problems, and image classification tasks on benchmark datasets, including MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100. SechKAN achieves superior performance compared to MLPs and other KAN variants while maintaining a similar number of parameters. However, its running time, while better than that of other KAN variants, is slightly longer than that of MLPs.
- 23 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSechKAN: Kolmogorov–Arnold Networks with Hyperbolic Secant Functions
SechKAN: Kolmogorov–Arnold Networks with Hyperbolic Secant FunctionsaIn recent years, Kolmogorov–Arnold Networks (KANs) have attracted increasing attention due to their effectiveness in machine learning and scientific computing tasks, offering a new paradigm for neural network design. In this paper, we present SechKAN, a KAN architecture based on hyperbolic secant (sech) functions. The hyperbolic secant basis is used for its smooth bell-shaped form, localized responses, and stable gradients. We employ 1D linear transformations to reduce the number of parameters, allowing SechKAN to remain comparable to multilayer perceptrons (MLPs) in model size. Experimental results indicate the effectiveness of SechKAN in function fitting, PDE problems, and image classification tasks on benchmark datasets, including MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100. SechKAN achieves superior performance compared to MLPs and other KAN variants while maintaining a similar number of parameters. However, its running time, while better than that of other KAN variants, is slightly longer than that of MLPs.
- Top Cited Papers
- 9 January 2026
- Published by Elsevier in Information Sciences
- Vol. 736
FC-KAN: Function combinations in Kolmogorov-Arnold networks
- 9 January 2026
- Published by Elsevier in Information Sciences
- Vol. 736
Top Cited PapersFC-KAN: Function combinations in Kolmogorov-Arnold networks
- Open Access
Combinations of Fast Activation and Trigonometric Functions in Kolmogorov-Arnold Networks
For years, many neural networks have been developed based on the Kolmogorov-Arnold Representation Theorem (KART), which was created to address Hilbert's 13th problem. Recently, relying on KART, Kolmogorov-Arnold Networks (KANs) have attracted attention from the research community, stimulating the use of polynomial functions such as B-splines and RBFs. However, these functions are not fully supported by GPU devices and are still considered less popular. In this paper, we propose the use of fast computational functions, such as ReLU and trigonometric functions (e.g., ReLU, sin, cos, arctan), as basis components in Kolmogorov-Arnold Networks (KANs). By integrating these function combinations into the network structure, we aim to enhance computational efficiency. Experimental results show that these combinations maintain competitive performance while offering potential improvements in training time and generalization.
Open AccessCombinations of Fast Activation and Trigonometric Functions in Kolmogorov-Arnold Networks
For years, many neural networks have been developed based on the Kolmogorov-Arnold Representation Theorem (KART), which was created to address Hilbert's 13th problem. Recently, relying on KART, Kolmogorov-Arnold Networks (KANs) have attracted attention from the research community, stimulating the use of polynomial functions such as B-splines and RBFs. However, these functions are not fully supported by GPU devices and are still considered less popular. In this paper, we propose the use of fast computational functions, such as ReLU and trigonometric functions (e.g., ReLU, sin, cos, arctan), as basis components in Kolmogorov-Arnold Networks (KANs). By integrating these function combinations into the network structure, we aim to enhance computational efficiency. Experimental results show that these combinations maintain competitive performance while offering potential improvements in training time and generalization.
- Top Cited Papers
- 28 April 2025
- Published by Springer Nature
- p. 3-15
BSRBF-KAN: A Combination of B-Splines and Radial Basis Functions in Kolmogorov-Arnold Networks
- 28 April 2025
- Published by Springer Nature
- p. 3-15
Top Cited PapersBSRBF-KAN: A Combination of B-Splines and Radial Basis Functions in Kolmogorov-Arnold Networks
- Open Access
AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning
Kolmogorov-Arnold Networks (KANs) have inspired numerous works exploring their applications across a wide range of scientific problems, with the potential to replace Multilayer Perceptrons (MLPs). While many KANs are designed using basis and polynomial functions, such as B-splines, ReLU-KAN utilizes a combination of ReLU functions to mimic the structure of B-splines and take advantage of ReLU's speed. However, ReLU-KAN is not built for multiple inputs, and its limitations stem from ReLU's handling of negative values, which can restrict feature extraction. To address these issues, we introduce Activation Function-Based Kolmogorov-Arnold Networks (AF-KAN), expanding ReLU-KAN with various activations and their function combinations. This novel KAN also incorporates parameter reduction methods, primarily attention mechanisms and data normalization, to enhance performance on image classification datasets. We explore different activation functions, function combinations, grid sizes, and spline orders to validate the effectiveness of AF-KAN and determine its optimal configuration. In the experiments, AF-KAN significantly outperforms MLP, ReLU-KAN, and other KANs with the same parameter count. It also remains competitive even when using fewer than 6 to 10 times the parameters while maintaining the same network structure. However, AF-KAN requires a longer training time and consumes more FLOPs. The repository for this work is available at https://github.com/hoangthangta/All-KAN.
Open AccessAF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning
Kolmogorov-Arnold Networks (KANs) have inspired numerous works exploring their applications across a wide range of scientific problems, with the potential to replace Multilayer Perceptrons (MLPs). While many KANs are designed using basis and polynomial functions, such as B-splines, ReLU-KAN utilizes a combination of ReLU functions to mimic the structure of B-splines and take advantage of ReLU's speed. However, ReLU-KAN is not built for multiple inputs, and its limitations stem from ReLU's handling of negative values, which can restrict feature extraction. To address these issues, we introduce Activation Function-Based Kolmogorov-Arnold Networks (AF-KAN), expanding ReLU-KAN with various activations and their function combinations. This novel KAN also incorporates parameter reduction methods, primarily attention mechanisms and data normalization, to enhance performance on image classification datasets. We explore different activation functions, function combinations, grid sizes, and spline orders to validate the effectiveness of AF-KAN and determine its optimal configuration. In the experiments, AF-KAN significantly outperforms MLP, ReLU-KAN, and other KANs with the same parameter count. It also remains competitive even when using fewer than 6 to 10 times the parameters while maintaining the same network structure. However, AF-KAN requires a longer training time and consumes more FLOPs. The repository for this work is available at https://github.com/hoangthangta/All-KAN.
- Open Access
- 1 January 2025
- Published by Elsevier in SSRN Electronic Journal
FC-KAN: Function Combinations in Kolmogorov-Arnold Networks
In this paper, we introduce FC-KAN, a Kolmogorov-Arnold Network (KAN) that leverages combinations of popular mathematical functions such as B-splines, wavelets, and radial basis functions on low-dimensional data through element-wise operations. We explore several methods for combining the outputs of these functions, including sum, element-wise product, the addition of sum and element-wise product, representations of quadratic and cubic functions, concatenation, linear transformation of the concatenated output, and others. In our experiments, we compare FC-KAN with a multi-layer perceptron network (MLP) and other existing KANs, such as BSRBF-KAN, EfficientKAN, FastKAN, and FasterKAN, on the MNIST and Fashion-MNIST datasets. Two variants of FC-KAN, which use a combination of outputs from B-splines and Difference of Gaussians (DoG) and from B-splines and linear transformations in the form of a quadratic function, outperformed overall other models on the average of 5 independent training runs. However, FC-KAN still has limitations, including challenges with parameter scalability and efficiency, as well as limited capability compared to CNNs when handling multi-channel datasets such as CIFAR-10. We expect that FC-KAN can leverage function combinations to design future KANs. Our repository is publicly available at: https://github.com/hoangthangta/FC_KAN.
- 1 January 2025
- Published by Elsevier in SSRN Electronic Journal
Open AccessFC-KAN: Function Combinations in Kolmogorov-Arnold Networks
In this paper, we introduce FC-KAN, a Kolmogorov-Arnold Network (KAN) that leverages combinations of popular mathematical functions such as B-splines, wavelets, and radial basis functions on low-dimensional data through element-wise operations. We explore several methods for combining the outputs of these functions, including sum, element-wise product, the addition of sum and element-wise product, representations of quadratic and cubic functions, concatenation, linear transformation of the concatenated output, and others. In our experiments, we compare FC-KAN with a multi-layer perceptron network (MLP) and other existing KANs, such as BSRBF-KAN, EfficientKAN, FastKAN, and FasterKAN, on the MNIST and Fashion-MNIST datasets. Two variants of FC-KAN, which use a combination of outputs from B-splines and Difference of Gaussians (DoG) and from B-splines and linear transformations in the form of a quadratic function, outperformed overall other models on the average of 5 independent training runs. However, FC-KAN still has limitations, including challenges with parameter scalability and efficiency, as well as limited capability compared to CNNs when handling multi-channel datasets such as CIFAR-10. We expect that FC-KAN can leverage function combinations to design future KANs. Our repository is publicly available at: https://github.com/hoangthangta/FC_KAN.
- 28 August 2024
- Published by Elsevier in Journal of Affective Disorders
- Vol. 366, 445-458
DepressionEmo: A novel dataset for multilabel classification of depression emotions
- 28 August 2024
- Published by Elsevier in Journal of Affective Disorders
- Vol. 366, 445-458
DepressionEmo: A novel dataset for multilabel classification of depression emotions
- Open Access
ThangDLU at #SMM4H 2024: Encoder-decoder models for classifying text data on social disorders in children and adolescents
This paper describes our participation in Task 3 and Task 5 of the #SMM4H (Social Media Mining for Health) 2024 Workshop, explicitly targeting the classification challenges within tweet data. Task 3 is a multi-class classification task centered on tweets discussing the impact of outdoor environments on symptoms of social anxiety. Task 5 involves a binary classification task focusing on tweets reporting medical disorders in children. We applied transfer learning from pre-trained encoder-decoder models such as BART-base and T5-small to identify the labels of a set of given tweets. We also presented some data augmentation methods to see their impact on the model performance. Finally, the systems obtained the best F1 score of 0.627 in Task 3 and the best F1 score of 0.841 in Task 5.
Open AccessThangDLU at #SMM4H 2024: Encoder-decoder models for classifying text data on social disorders in children and adolescents
This paper describes our participation in Task 3 and Task 5 of the #SMM4H (Social Media Mining for Health) 2024 Workshop, explicitly targeting the classification challenges within tweet data. Task 3 is a multi-class classification task centered on tweets discussing the impact of outdoor environments on symptoms of social anxiety. Task 5 involves a binary classification task focusing on tweets reporting medical disorders in children. We applied transfer learning from pre-trained encoder-decoder models such as BART-base and T5-small to identify the labels of a set of given tweets. We also presented some data augmentation methods to see their impact on the model performance. Finally, the systems obtained the best F1 score of 0.627 in Task 3 and the best F1 score of 0.841 in Task 5.