
Augmenting Molecular Deep Generative Models with Topological Data Analysis Representations
Deep generative models have emerged as a powerful tool for learning info...
read it

Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI
In this paper, we describe an open source Python toolkit named Uncertain...
read it

Finding the Homology of Decision Boundaries with Active Learning
Accurately and efficiently characterizing the decision boundary of class...
read it

Characterizing the Latent Space of Molecular Deep Generative Models with Persistent Homology Metrics
Deep generative models are increasingly becoming integral parts of the i...
read it

Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness
Mode connectivity provides novel geometric insights on analyzing loss la...
read it

Model Agnostic Multilevel Explanations
In recent years, posthoc local instancelevel and global datasetlevel ...
read it

Drug Repurposing for Cancer: An NLP Approach to Identify LowCost Therapies
More than 200 generic drugs approved by the U.S. Food and Drug Administr...
read it

Understanding racial bias in health using the Medical Expenditure Panel Survey data
Over the years, several studies have demonstrated that there exist signi...
read it

Teaching AI to Explain its Decisions Using Embeddings and MultiTask Learning
Using machine learning in highstakes applications often requires predic...
read it

PINet: A Deep Learning Approach to Extract Topological Persistence Images
Topological features such as persistence diagrams and their functional a...
read it

Optimized Score Transformation for Fair Classification
This paper considers fair probabilistic classification where the outputs...
read it

Counting and Segmenting Sorghum Heads
Phenotyping is the process of measuring an organism's observable traits....
read it

Crowd Counting with Decomposed Uncertainty
Research in neural networks in the field of computer vision has achieved...
read it

Bias Mitigation Postprocessing for Individual and Group Fairness
Whereas previous postprocessing approaches for increasing the fairness ...
read it

TED: Teaching AI to Explain its Decisions
Artificial intelligence systems are being increasingly deployed due to t...
read it

AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Fairness is an increasingly important concern as machine learning models...
read it

Increasing Trust in AI Services through Supplier's Declarations of Conformity
The accuracy and reliability of machine learning algorithms are an impor...
read it

Perturbation Robust Representations of Topological Persistence Diagrams
Topological methods for data analysis present opportunities for enforcin...
read it

Teaching Meaningful Explanations
The adoption of machine learning in highstakes applications such as hea...
read it

Topological Data Analysis of Decision Boundaries with Application to Model Selection
We propose the labeled Čech complex, the plain labeled VietorisRips com...
read it

Simultaneous Parameter Learning and BiClustering for MultiResponse Models
We consider multiresponse and multitask regression models, where the pa...
read it

Exploring HighDimensional Structure via AxisAligned Decomposition of Linear Projections
Twodimensional embeddings remain the dominant approach to visualize hig...
read it

DistributionPreserving kAnonymity
Preserving the privacy of individuals by protecting their sensitive attr...
read it

An EndToEnd Machine Learning Pipeline That Ensures Fairness Policies
In consequential realworld applications, machine learning (ML) based sy...
read it

Multitask Learning using Task Clustering with Applications to Predictive Modeling and GWAS of Plant Varieties
Inferring predictive maps between multiple input and multiple output var...
read it

Distributed Bundle Adjustment
Most methods for Bundle Adjustment (BA) in computer vision are either ce...
read it

Learning Robust Representations for Computer Vision
Unsupervised learning techniques in computer vision often require learni...
read it

Shape Parameter Estimation
Performance of machine learning approaches depends strongly on the choic...
read it

Optimized Data PreProcessing for Discrimination Prevention
Nondiscrimination is a recognized objective in algorithmic decision mak...
read it

A Deep Learning Approach To Multiple Kernel Fusion
Kernel fusion is a popular and effective approach for combining multiple...
read it

A Riemannian Framework for Statistical Analysis of Topological Persistence Diagrams
Topological data analysis is becoming a popular way to study high dimens...
read it

Persistent Homology of Attractors For Action Recognition
In this paper, we propose a novel framework for dynamical analysis of hu...
read it

Automatic Inference of the Quantile Parameter
Supervised learning is an active research area, with numerous applicatio...
read it

Beyond L2Loss Functions for Learning Sparse Models
Incorporating sparsity priors in learning tasks can give rise to simple,...
read it

Recovering Nonnegative and Combined Sparse Representations
The nonnegative solution to an underdetermined linear system can be uni...
read it

Learning Stable Multilevel Dictionaries for Sparse Representations
Sparse representations using learned dictionaries are being increasingly...
read it
Karthikeyan Natesan Ramamurthy
is this you? claim profile
Research Staff Member at IBM Thomas J Watson Research Center