Transfer Learning paper acceptance!
Congratulations to Dr Nagender and his team, who published the paper, Transfer learning for cancer diagnosis in histopathological images
Dr Nagender’s paper on “Transfer learning for cancer diagnosis in histopathological images” has been accepted at IAES International Journal of Artificial Intelligence (IJ-AI).
In this paper, Dr Nagender and his team use 14 pre-trained ImageNet models to perform transfer learning, to transfer the knowledge learned from one task to be applied on another, on histopathologic cancer detection dataset. Each of the 14 models has been configured as naive model, feature extractor model, or fine-tuned model. From their study, they found that Densenet161 demonstrated high precision while Resnet101 high recall. A high precision model is suitable when follow-up examination cost is high. A model with low precision but a high recall/sensitivity is useful when follow-up examination cost is low. Transfer learning was found to help converge a model faster.
The full PDF text is available here.
Dr Nagender’s research interests are: Deep Learning, Adversarial Machine Learning, Computer Vision, Natural Language Processing, Deep Reinforcement Learning.
For research collaboration or supervision opportunities with Dr Nagender, kindly refer to his profile page here.
Universiti Brunei Darussalam
Jalan Tungku Link, BE1410
Negara Brunei Darussalam