Prasanna Sattigeri

verfied profile

∙ 0 followers
ibm

A Maximal Correlation Approach to Imposing Fairness in Machine Learning

As machine learning algorithms grow in popularity and diversify to many ...
12/30/2020 ∙ by Joshua Lee, et al. ∙ 0 ∙ share

read it
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty

Transparency of algorithmic systems entails exposing system properties t...
11/15/2020 ∙ by Umang Bhatt, et al. ∙ 6 ∙ share

read it
Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modelling

Current autoencoder-based disentangled representation learning methods a...
10/25/2020 ∙ by Akash Srivastava, et al. ∙ 8 ∙ share

read it
not-so-BigGAN: Generating High-Fidelity Images on a Small Compute Budget

BigGAN is the state-of-the-art in high-resolution image generation, succ...
09/09/2020 ∙ by Seungwook Han, et al. ∙ 14 ∙ share

read it
Optimizing Mode Connectivity via Neuron Alignment

The loss landscapes of deep neural networks are not well understood due ...
09/05/2020 ∙ by N. Joseph Tatro, et al. ∙ 5 ∙ share

read it
AR-Net: Adaptive Frame Resolution for Efficient Action Recognition

Action recognition is an open and challenging problem in computer vision...
07/31/2020 ∙ by Yue Meng, et al. ∙ 4 ∙ share

read it
OnlineAugment: Online Data Augmentation with Less Domain Knowledge

Data augmentation is one of the most important tools in training modern ...
07/17/2020 ∙ by Zhiqiang Tang, et al. ∙ 15 ∙ share

read it
Fair Data Integration

The use of machine learning (ML) in high-stakes societal decisions has e...
06/10/2020 ∙ by Sainyam Galhotra, et al. ∙ 39 ∙ share

read it
Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models

The wide-spread adoption of representation learning technologies in clin...
04/27/2020 ∙ by Jayaraman J. Thiagarajan, et al. ∙ 22 ∙ share

read it
StarNet: towards weakly supervised few-shot detection and explainable few-shot classification

In this paper, we propose a new few-shot learning method called StarNet,...
03/15/2020 ∙ by Leonid Karlinsky, et al. ∙ 25 ∙ share

read it
TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification

The field of Few-Shot Learning (FSL), or learning from very few (typical...
03/14/2020 ∙ by Moshe Lichtenstein, et al. ∙ 12 ∙ share

read it
Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration

The hypothesis that sub-network initializations (lottery) exist within t...
02/10/2020 ∙ by Bindya Venkatesh, et al. ∙ 5 ∙ share

read it
Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies

More than 200 generic drugs approved by the U.S. Food and Drug Administr...
11/18/2019 ∙ by Shivashankar Subramanian, et al. ∙ 30 ∙ share

read it
Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets

Recent advances in computer vision and deep learning have led to breakth...
10/29/2019 ∙ by Newton M. Kinyanjui, et al. ∙ 36 ∙ share

read it
Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictors

With rapid adoption of deep learning in high-regret applications, the qu...
09/09/2019 ∙ by Jayaraman J. Thiagarajan, et al. ∙ 0 ∙ share

read it
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

As artificial intelligence and machine learning algorithms make further ...
09/06/2019 ∙ by Vijay Arya, et al. ∙ 36 ∙ share

read it
Generating Contrastive Explanations with Monotonic Attribute Functions

Explaining decisions of deep neural networks is a hot research topic wit...
05/29/2019 ∙ by Ronny Luss, et al. ∙ 9 ∙ share

read it
Understanding Unequal Gender Classification Accuracy from Face Images

Recent work shows unequal performance of commercial face classification ...
11/30/2018 ∙ by Vidya Muthukumar, et al. ∙ 0 ∙ share

read it
Co-regularized Alignment for Unsupervised Domain Adaptation

Deep neural networks, trained with large amount of labeled data, can fai...
11/13/2018 ∙ by Abhishek Kumar, et al. ∙ 0 ∙ share

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...
10/03/2018 ∙ by Rachel K. E. Bellamy, et al. ∙ 12 ∙ share

read it
Can Deep Clinical Models Handle Real-World Domain Shifts?

The hypothesis that computational models can be reliable enough to be ad...
09/20/2018 ∙ by Jayaraman J. Thiagarajan, et al. ∙ 0 ∙ share

read it
Fairness GAN

In this paper, we introduce the Fairness GAN, an approach for generating...
05/24/2018 ∙ by Prasanna Sattigeri, et al. ∙ 0 ∙ share

read it
Optimizing Kernel Machines using Deep Learning

Building highly non-linear and non-parametric models is central to sever...
11/15/2017 ∙ by Huan Song, et al. ∙ 0 ∙ share

read it
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations

Disentangled representations, where the higher level data generative fac...
11/02/2017 ∙ by Abhishek Kumar, et al. ∙ 0 ∙ share

read it
Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference

Semi-supervised learning methods using Generative Adversarial Networks (...
05/24/2017 ∙ by Abhishek Kumar, et al. ∙ 0 ∙ share

read it
A Deep Learning Approach To Multiple Kernel Fusion

Kernel fusion is a popular and effective approach for combining multiple...
12/28/2016 ∙ by Huan Song, et al. ∙ 0 ∙ share

read it
Understanding Innovation to Drive Sustainable Development

Innovation is among the key factors driving a country's economic and soc...
06/15/2016 ∙ by Prasanna Sattigeri, et al. ∙ 0 ∙ share

read it

Prasanna Sattigeri

Featured Co-authors

Kate Saenko

Pin-Yu Chen

Raja Giryes

Kai Xu

William T. Freeman

Kush R. Varshney

Jayaraman J. Thiagarajan

Adrian Weller

Rogerio Feris

Abhishek Kumar

Karthikeyan Natesan Ramamurthy

A Maximal Correlation Approach to Imposing Fairness in Machine Learning

Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty

Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modelling

not-so-BigGAN: Generating High-Fidelity Images on a Small Compute Budget

Optimizing Mode Connectivity via Neuron Alignment

AR-Net: Adaptive Frame Resolution for Efficient Action Recognition

OnlineAugment: Online Data Augmentation with Less Domain Knowledge

Fair Data Integration

Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models

StarNet: towards weakly supervised few-shot detection and explainable few-shot classification

TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification

Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration

Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies

Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets

Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictors

One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

Generating Contrastive Explanations with Monotonic Attribute Functions

Understanding Unequal Gender Classification Accuracy from Face Images

Co-regularized Alignment for Unsupervised Domain Adaptation

AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias

Can Deep Clinical Models Handle Real-World Domain Shifts?

Fairness GAN

Optimizing Kernel Machines using Deep Learning

Variational Inference of Disentangled Latent Concepts from Unlabeled Observations

Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference

A Deep Learning Approach To Multiple Kernel Fusion

Understanding Innovation to Drive Sustainable Development