Karthikeyan Natesan Ramamurthy
Publications 116
#1Chung-Ching Lin (IBM)H-Index: 7
Last.Sharathchandra U. Pankanti (IBM)H-Index: 45
view all 3 authors...
To date, billions of cameras have been actively used on moving platform. Video analytics applications for camera are emerging in diverse areas. Among various video analytics applications for moving cameras, we will discuss the application of unmanned aerial vehicles (UAVs). First, we present a system for summarizing videos by automatically creating a panorama for videos, detecting and tracking moving objects in the videos. Our video summarization experiments on the UAV dataset demonstrate that w...
#1Ming Yu (U of C: University of Chicago)H-Index: 3
Last.Aurelie C. Lozano (IBM)H-Index: 15
view all 4 authors...
We consider multi-response and multi-task regression models, where the parameter matrix to be estimated is expected to have an unknown grouping structure. The groupings can be along tasks, or features, or both, the last one indicating a bi-cluster or "checkerboard" structure. Discovering this grouping structure along with parameter inference makes sense in several applications, such as multi-response Genome-Wide Association Studies (GWAS). By inferring this additional structure we can obtain val...
#1Rachel K. E. Bellamy (IBM)H-Index: 23
#2Kuntal Dey (IBM)H-Index: 8
Last.Yunfeng Zhang (IBM)H-Index: 5
view all 17 authors...
Today, machine-learning software is used to help make decisions that affect people's lives. Some people believe that the application of such software results in fairer decisions because, unlike humans, machine-learning software generates models that are not biased. Think again. Machine-learning software is also biased, sometimes in similar ways to humans, often in different ways. While fair model- assisted decision making involves more than the application of unbiased models-consideration of app...
Jun 9, 2019 in ICML (International Conference on Machine Learning)
#2Kush R. Varshney (IBM)H-Index: 18
Last.Krishnan Mody (NYU: New York University)H-Index: 2
view all 3 authors...
2 Citations
Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and computer vision applications. Key bottlenecks to their large scale adoption are computational expenditure and difficulty in incorporating them in a differentiable architecture. We take an important step in this paper to mitigate these bottlenecks by proposing a novel one-step approach to generate PIs directly from the i...
Jan 27, 2019 in AAAI (National Conference on Artificial Intelligence)
#1Michael Hind (IBM)H-Index: 25
#2Dennis Wei (IBM)H-Index: 14
Last.Kush R. Varshney (IBM)H-Index: 18
view all 8 authors...
Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions. However, as many of these systems are opaque in their operation, there is a growing demand for such systems to provide explanations for their decisions. Conventional approaches to this problem attempt to expose or discover the inner workings of a machine learning model with the hope that the resulting explanations will be mean...
3 CitationsSource
#1Noel C. F. CodellaH-Index: 18
#2Michael Hind (IBM)H-Index: 25
Last.Aleksandra MojsilovicH-Index: 24
view all 8 authors...
Using machine learning in high-stakes applications often requires predictions to be accompanied by explanations comprehensible to the domain user, who has ultimate responsibility for decisions and outcomes. Recently, a new framework for providing explanations, called TED, has been proposed to provide meaningful explanations for predictions. This framework augments training data to include explanations elicited from domain users, in addition to features and labels. This approach ensures that expl...
#1Min-hwan Oh (Columbia University)H-Index: 3
#2Peder A. OlsenH-Index: 22
Last.Karthikeyan Natesan Ramamurthy (IBM)H-Index: 14
view all 3 authors...
Phenotyping is the process of measuring an organism's observable traits. Manual phenotyping of crops is a labor-intensive, time-consuming, costly, and error prone process. Accurate, automated, high-throughput phenotyping can relieve a huge burden in the crop breeding pipeline. In this paper, we propose a scalable, high-throughput approach to automatically count and segment panicles (heads), a key phenotype, from aerial sorghum crop imagery. Our counting approach uses the image density map obtain...
#1Dennis WeiH-Index: 14
Last.Flavio du Pin CalmonH-Index: 15
view all 3 authors...
This paper considers fair probabilistic classification where the outputs of primary interest are predicted probabilities, commonly referred to as scores. We formulate the problem of transforming scores to satisfy fairness constraints that are linear in conditional means of scores while minimizing the loss in utility. The same formulation can be applied both to post-process classifier outputs as well as to pre-process training data. We derive a closed-form expression for the optimal transformed s...
Jan 1, 2019 in AAAI (National Conference on Artificial Intelligence)
#1Amanda Coston (CMU: Carnegie Mellon University)H-Index: 1
Last.Supriyo Chakraborty (IBM)H-Index: 14
view all 7 authors...
8 CitationsSource