Back
  1. Home
  2. Profile of Panissara THANAPOL (Unilu)
Profil

THANAPOL Panissara

Main Referenced Co-authors
BOUVRY, Pascal  (2)
LEPREVOST, Franck  (2)
LAVANGNANANDA, Kittichai  (1)
Lavangnananda, Kittichai (1)
PINEL, Frederic  (1)
Main Referenced Keywords
Computer Science (all) (1); Deep learning (1); Distributed Training (1); Distributed training (1); GPU Cluster (1);
Main Referenced Unit & Research Centers
ULHPC - University of Luxembourg: High Performance Computing (1)
Main Referenced Disciplines
Computer science (2)

Publications (total 2)

The most downloaded
362 downloads
Thanapol, P., Lavangnananda, K., Bouvry, P., Pinel, F., & Leprevost, F. (2020). Reducing overfitting and improving generalization in training convolutional neural network under limited sample sizes in image recognition. In 5th International Conference on Information Technology, Bangsaen 21-22 October 2020 (pp. 300-305). https://hdl.handle.net/10993/45107

The most cited

38 citations (Scopus®)

Thanapol, P., Lavangnananda, K., Bouvry, P., Pinel, F., & Leprevost, F. (2020). Reducing overfitting and improving generalization in training convolutional neural network under limited sample sizes in image recognition. In 5th International Conference on Information Technology, Bangsaen 21-22 October 2020 (pp. 300-305). https://hdl.handle.net/10993/45107

THANAPOL, P., LAVANGNANANDA, K., LEPREVOST, F., SCHLEICH, J., & BOUVRY, P. (2023). Scheduling Deep Learning Training in GPU Cluster Using the Model-Similarity-Based Policy. In N. T. Nguyen & B. Hnatkowska (Eds.), Intelligent Information and Database Systems - 15th Asian Conference, ACIIDS 2023, Proceedings. Springer Science and Business Media Deutschland GmbH. doi:10.1007/978-981-99-5837-5_30
Peer reviewed

Thanapol, P., Lavangnananda, K., Bouvry, P., Pinel, F., & Leprevost, F. (2020). Reducing overfitting and improving generalization in training convolutional neural network under limited sample sizes in image recognition. In 5th International Conference on Information Technology, Bangsaen 21-22 October 2020 (pp. 300-305).
Peer reviewed

Contact ORBilu