Search Results for author:
Found 16 papers, 5 papers with code
Interactive Visual Learning for Stable Diffusion
Diffusion-based generative models' impressive ability to create convincing images has garnered global attention.
Using Guided Transfer Learning to Predispose AI Agent to Learn Efficiently from Small RNA-sequencing Datasets
In this work we look at how transfer learning can be improved to learn from small RNA-seq sample sizes without significant human interference.
Trigonometric Quadrature Fourier Features for Scalable Gaussian Process Regression
Fourier feature approximations have been successfully applied in the literature for scalable Gaussian Process (GP) regression.
Explainable machine learning identifies multi-omics signatures of muscle response to spaceflight in mice
The adverse effects of microgravity exposure on mammalian physiology during spaceflight necessitate a deep understanding of the underlying mechanisms to develop effective countermeasures.
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs
Our research aims to unify existing works' diverging opinions on how architectural components affect the adversarial robustness of CNNs.
Additive Multi-Index Gaussian process modeling, with application to multi-physics surrogate modeling of the quark-gluon plasma
The Quark-Gluon Plasma (QGP) is a unique phase of nuclear matter, theorized to have filled the Universe shortly after the Big Bang.
Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion
Diffusion Explainer tightly integrates a visual overview of Stable Diffusion's complex components with detailed explanations of their underlying operations, enabling users to fluidly transition between multiple levels of abstraction through animations and interactive elements.
RobArch: Designing Robust Architectures against Adversarial Attacks
Adversarial Training is the most effective approach for improving the robustness of Deep Neural Networks (DNNs).
Neighboring state-based RL Exploration
Reinforcement Learning is a powerful tool to model decision-making processes.
NeuroMapper: In-browser Visualizer for Neural Network Training
We present our ongoing work NeuroMapper, an in-browser visualization tool that helps machine learning (ML) developers interpret the evolution of a model during training, providing a new way to monitor the training process and visually discover reasons for suboptimal training.
Beyond Bayes-optimality: meta-learning what you know you don't know
This is in contrast to risk-sensitive agents, which additionally exploit the higher-order moments of the return, and ambiguity-sensitive agents, which act differently when recognizing situations in which they lack knowledge.
Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and Discoveries
We present ConceptEvo, a unified interpretation framework for deep neural networks (DNNs) that reveals the inception and evolution of learned concepts during training.
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning
In this work, we show that an uncertainty aware classifier can solve challenging reinforcement learning problems by both encouraging exploration and provided directed guidance towards positive outcomes.
Reinforcement Learning with Bayesian Classifiers: Efficient Skill Learning from Outcome Examples
In this work, we study a more tractable class of reinforcement learning problems defined by data that provides examples of successful outcome states.
FlowDB a large scale precipitation, river, and flash flood dataset
We introduce a novel hourly river flow and precipitation dataset and a second subset of flash flood events with damage estimates and injury counts.
Asymptotic Normality for Multivariate Random Forest Estimators
Regression trees and random forests are popular and effective non-parametric estimators in practical applications.
