activity
20142023
most citedNeural Networks with Smooth Adaptive Activation Functions for Regression

14 citations · 18 across the 7 of their papers we have counts for

collaborators

6 papers

cs.CV20221 cited

Learning Topological Interactions for Multi-Class Medical Image Segmentation

Saumya Gupta, Xiaoling Hu, James Kaan +10

Deep learning methods have achieved impressive performance for multi-class medical image segmentation. However, they are limited in their ability to encode topological interactions…

cs.DC20201 cited

In-situ Workflow Auto-tuning via Combining Performance Models of Component Applications

Tong Shu, Yanfei Guo, Justin Wozniak +3

In-situ parallel workflows couple multiple component applications, such as simulation and analysis, via streaming data transfer. in order to avoid data exchange via shared file sys…

cs.CV20172 cited

Center-Focusing Multi-task CNN with Injected Features for Classification of Glioma Nuclear Images

Veda Murthy, Le Hou, Dimitris Samaras +2

Classifying the various shapes and attributes of a glioma cell nucleus is crucial for diagnosis and understanding the disease. We investigate automated classification of glioma nuc…

cs.DC2016

Efficient Methods and Parallel Execution for Algorithm Sensitivity Analysis with Parameter Tuning on Microscopy Imaging Datasets

George Teodoro, Tahsin Kurc, Luis F. R. Taveira +3

Background: We describe an informatics framework for researchers and clinical investigators to efficiently perform parameter sensitivity analysis and auto-tuning for algorithms tha…

cs.CV201614 cited

Neural Networks with Smooth Adaptive Activation Functions for Regression

Le Hou, Dimitris Samaras, Tahsin M. Kurc +2

In Neural Networks (NN), Adaptive Activation Functions (AAF) have parameters that control the shapes of activation functions. These parameters are trained along with other paramete…

cs.DC2014

Region Templates: Data Representation and Management for Large-Scale Image Analysis

George Teodoro, Tony Pan, Tahsin Kurc +4

Distributed memory machines equipped with CPUs and GPUs (hybrid computing nodes) are hard to program because of the multiple layers of memory and heterogeneous computing configurat…