Santanu Santra
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
Santanu Santra has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Cheng-Han Chou
College of Artificial Intelligence and Green Energy, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
1 shared publication Chi-Fang Lin
Department of Computer Science and Engineering, Yuan Ze University, Taoyuan, Taiwan
1 shared publication- Chih-Sheng Huang
Department of Artificial Intelligence Research and Development, Elan Microelectronics Corporation, Hsinchu, Taiwan; College of Artificial Intelligence and Green Energy, National Yang Ming Chiao Tung University, Hsinchu, Taiwan; College of Electrical Engineering and Computer Science, National Taipei University of Technology, Taipei, Taiwan
1 shared publication Jun-Wei Hsieh
College of Artificial Intelligence and Green Energy, National Chiao Tung University, Hsinchu, Taiwan
1 shared publication- Jun-Wei Hsieh
National yang Ming Chiao Tung University
1 shared publication - Ming-Ching Chang
University at Albany
1 shared publication
Latest Publications
- 7 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (3) , 1235-1246
Mean-Shift Based Differentiable Architecture Search
Differentiable Architecture Search (DARTS) is an effective continuous relaxation-based network architecture search (NAS) method with low search cost. It has attracted significant attention in AutoML research and has become one of the most effective paradigms in NAS. Although DARTS comes with great efficiency over traditional NAS approaches in handling the complex parameter search process, it often suffers from stabilization issues in producing deteriorating architectures when discretizing the found continuous architecture. To address this issue, we propose a Mean-Shift based DARTS (MS-DARTS) to improve the stability based on architecture sampling, perturbation, and shifting. The proposed mean-shift approach in MS-DARTS can effectively improve the stability and accuracy of DARTS by smoothing the loss landscape and sampling the architecture parameters within a suitable bandwidth. We investigate the convergence of our mean-shift approach as well as the effects of bandwidth selection towards stability and accuracy optimization. Evaluations on CIFAR-10, CIFAR-100, and ImageNet show that MS-DARTS archives competitive performance among state-ofthe-art NAS methods with reduced search cost.
- 7 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (3) , 1235-1246
Mean-Shift Based Differentiable Architecture Search
Differentiable Architecture Search (DARTS) is an effective continuous relaxation-based network architecture search (NAS) method with low search cost. It has attracted significant attention in AutoML research and has become one of the most effective paradigms in NAS. Although DARTS comes with great efficiency over traditional NAS approaches in handling the complex parameter search process, it often suffers from stabilization issues in producing deteriorating architectures when discretizing the found continuous architecture. To address this issue, we propose a Mean-Shift based DARTS (MS-DARTS) to improve the stability based on architecture sampling, perturbation, and shifting. The proposed mean-shift approach in MS-DARTS can effectively improve the stability and accuracy of DARTS by smoothing the loss landscape and sampling the architecture parameters within a suitable bandwidth. We investigate the convergence of our mean-shift approach as well as the effects of bandwidth selection towards stability and accuracy optimization. Evaluations on CIFAR-10, CIFAR-100, and ImageNet show that MS-DARTS archives competitive performance among state-ofthe-art NAS methods with reduced search cost.
- Open Access
- 21 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 89602-89618
Gradient Descent Effects on Differential Neural Architecture Search: A Survey
Gradient Descent, an effective way to search for the local minimum of a function, can minimize training and validation loss of neural architectures and also be incited in an appropriate order to decrease the searching cost of neural architecture search. In recent trends, the neural architecture search (NAS) is enormously used to construct an automatic architecture for a specific task. Mostly well-performed neural architecture search methods have adopted reinforcement learning, evolutionary algorithms, or gradient descent algorithms to find the best-performing candidate architecture. Among these methods, gradient descent-based architecture search approaches outperform all other methods in terms of efficiency, simplicity, computational cost, and validation error. In view of this, an in-depth survey is necessary to cover the usefulness of gradient descent method and how this can benefit neural architecture search. We begin our survey with basic concepts of neural architecture search, gradient descent, and their unique properties. Our survey then delves into the impact of gradient descent method on NAS and explores the effect of gradient descent in the search process to generate the candidate architecture. At the same time, our survey reviews mostly used gradient-based search approaches in NAS. Finally, we provide the current research challenges and open problems in the NAS-based approaches, which need to be addressed in future research.
- 21 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 89602-89618
Open AccessGradient Descent Effects on Differential Neural Architecture Search: A Survey
Gradient Descent, an effective way to search for the local minimum of a function, can minimize training and validation loss of neural architectures and also be incited in an appropriate order to decrease the searching cost of neural architecture search. In recent trends, the neural architecture search (NAS) is enormously used to construct an automatic architecture for a specific task. Mostly well-performed neural architecture search methods have adopted reinforcement learning, evolutionary algorithms, or gradient descent algorithms to find the best-performing candidate architecture. Among these methods, gradient descent-based architecture search approaches outperform all other methods in terms of efficiency, simplicity, computational cost, and validation error. In view of this, an in-depth survey is necessary to cover the usefulness of gradient descent method and how this can benefit neural architecture search. We begin our survey with basic concepts of neural architecture search, gradient descent, and their unique properties. Our survey then delves into the impact of gradient descent method on NAS and explores the effect of gradient descent in the search process to generate the candidate architecture. At the same time, our survey reviews mostly used gradient-based search approaches in NAS. Finally, we provide the current research challenges and open problems in the NAS-based approaches, which need to be addressed in future research.
- 1 April 2008
- Published by Elsevier in Pattern Recognition
- Vol. 41 (4) , 1338-1349
A genetic approach for efficient outlier detection in projected space
- 1 April 2008
- Published by Elsevier in Pattern Recognition
- Vol. 41 (4) , 1338-1349
A genetic approach for efficient outlier detection in projected space