sivaramakrishnan-rajaraman
Goto Github
PK
Name: Sivaramakrishnan Rajaraman
Type: User
Company: National Library of Medicine, National Institutes of Health, USA
Bio: Dr. Sivarama Krishnan Rajaraman holds the position of Deep Learning Research Scientist at the Lister Hill Center, National Library of Medicine, NIH, USA.
Location: Bethesda, Maryland, USA
Blog: https://lhncbc.nlm.nih.gov/personnel/sivaramakrishnan-rajaraman
Sivaramakrishnan Rajaraman's Projects
DoubleU-Net for Semantic Image Segmentation in TensorFlow Keras (Nominated for Best Paper Award (IEEE CBMS))
Active Learning on Image Data using Bayesian ConvNets
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
This is a reimplementation of AG-CNN. ("Thorax Disease Classification with Attention Guided Convolutional Neural Network","Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification")
CNN Deep Learning Model using Keras for predicting the Age
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
Augmentations usage examples for albumentations library
Algorithms for monitoring and explaining machine learning models
Amazing Semantic Segmentation on Tensorflow && Keras (include FCN, UNet, SegNet, PSPNet, PAN, RefineNet, DeepLabV3, DeepLabV3+, DenseASPP, BiSegNet)
pip install antialiased-cnns to improve stability and accuracy
draw ROC,PR curve and calculate AUC MAP IoU for image semantic segmentation problem
A collection of research materials on explainable AI/ML
Source code for "One simple trick to train Keras model faster with Batch Normalization"
Building a Bayesian deep learning classifier
BCCD (Blood Cell Count and Detection) Dataset is a small-scale dataset for blood cells detection.
BCDU-Net : Medical Image Segmentation
Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)
Keras implementation of BlurPool layers described in "Making Convolutional Networks Shift-Invariant Again" (Zhang)
This study proposes a bone suppression model ensemble using novel and state-of-the-art deep learning architectures
A boosting framework, consisting of a DCNN for multi-label semantic segmentation with a customized logarithmic-Dice loss function, a fusion module combining the original labels and the corresponding predictions from the DCNN, and a boosting algorithm to sequentially update the sample weights during network training iterations, is proposed to systematically improve the quality of the annotated data, resulting in eventually the performance improvement of the segmentation tasks
Multi-Instance-Learning to check breast cancer. An implementation of Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification[arXiv:1504.07947] https://arxiv.org/abs/1504.07947
A Keras implementation of CapsNet in Hinton's paper Dynamic Routing Between Capsules. Now Val_acc>99.5%.