Data Science & AI Research

research

∙ 11/03/2022

Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems

We develop inductive biases for the machine learning of complex physical...

Quercus Hernandez, et al. ∙

research

∙ 11/02/2022

Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach

Data augmentation is a critical contributing factor to the success of de...

Kaiwen Yang, et al. ∙

research

∙ 11/15/2022

ABANICCO: A New Color Space for Multi-Label Pixel Classification and Color Segmentation

In any computer vision task involving color images, a necessary step is ...

Laura Nicolás-Sáenz, et al. ∙

research

∙ 11/17/2022

Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks

Despite the remarkable success of foundation models, their task-specific...

Hao Li, et al. ∙

research

∙ 11/21/2022

Can You Label Less by Using Out-of-Domain Data? Active Transfer Learning with Few-shot Instructions

Labeling social-media data for custom dimensions of toxicity and social ...

Rafal Kocielnik, et al. ∙

research

∙ 11/16/2022

Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN

Auditing machine learning-based (ML) healthcare tools for bias is critic...

Anaelia Ovalle, et al. ∙

research

∙ 11/14/2022

Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computing

Recent breakthroughs in computing power have made it feasible to use mac...

Salah A Faroughi, et al. ∙

research

∙ 11/15/2022

Normalizing Flows for Hierarchical Bayesian Analysis: A Gravitational Wave Population Study

We propose parameterizing the population distribution of the gravitation...

David Ruhe, et al. ∙

research

∙ 11/02/2022

Variational Hierarchical Mixtures for Learning Probabilistic Inverse Dynamics

Well-calibrated probabilistic regression models are a crucial learning c...

Hany Abdulsamad, et al. ∙

research

∙ 11/16/2022

Holistic Evaluation of Language Models

Language models (LMs) are becoming the foundation for almost all major l...

Percy Liang, et al. ∙

research

∙ 11/01/2022

Exploring Effects of Computational Parameter Changes to Image Recognition Systems

Image recognition tasks typically use deep learning and require enormous...

Nikolaos Louloudakis, et al. ∙