66 citations · 168 across the 35 of their papers we have counts for
8 papers · 1 filter
Confidence Calibration for Systems with Cascaded Predictive Modules
Yunye Gong, Yi Yao, Xiao Lin +2
Existing conformal prediction algorithms estimate prediction intervals at target confidence levels to characterize the performance of a regression model on new test samples. Howeve…
System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games
Indranil Sur, Zachary Daniels, Abrar Rahman +16
As Artificial and Robotic Systems are increasingly deployed and relied upon for real-world applications, it is important that they exhibit the ability to continually learn and adap…
Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2
Zachary Daniels, Aswin Raghavan, Jesse Hostetler +4
One approach to meet the challenges of deep lifelong reinforcement learning (LRL) is careful management of the agent's learning experiences, to learn (without forgetting) and build…
Confidence Calibration for Domain Generalization under Covariate Shift
Yunye Gong, Xiao Lin, Yi Yao +3
Existing calibration algorithms address the problem of covariate shift via unsupervised domain adaptation. However, these methods suffer from the following limitations: 1) they req…
Detecting Trojaned DNNs Using Counterfactual Attributions
Karan Sikka, Indranil Sur, Susmit Jha +2
We target the problem of detecting Trojans or backdoors in DNNs. Such models behave normally with typical inputs but produce specific incorrect predictions for inputs poisoned with…
Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer
Aswin Raghavan, Jesse Hostetler, Indranil Sur +2
We introduce the eigentask framework for lifelong learning. An eigentask is a pairing of a skill that solves a set of related tasks, paired with a generative model that can sample…
Progressive Growing of Neural ODEs
Hammad A. Ayyubi, Yi Yao, Ajay Divakaran
Neural Ordinary Differential Equations (NODEs) have proven to be a powerful modeling tool for approximating (interpolation) and forecasting (extrapolation) irregularly sampled time…
Data-Efficient Mutual Information Neural Estimator
Xiao Lin, Indranil Sur, Samuel A. Nastase +3
Measuring Mutual Information (MI) between high-dimensional, continuous, random variables from observed samples has wide theoretical and practical applications. Recent work, MINE (B…