Search for tag: "learning"

Towards Provable Unaligned Multimodal Learning: A Model Identification Perspective

Inverse Constraint Learning and Risk-Averse Reinforcement Learning for Safe AI

Training Machines to Know What They Don't Know

Deep Learning for Radio Frequency Device Finger Printing

Towards Automated Data Mining: Reinforcement Intelligence for Self-Optimizing Feature Engineering

When Sparse Data is All You Have: Learning World Models for Generalizable Planning and RL with a View Towards AI Asessment

Towards Safe and Actionable AI: Strategies for Robust Adaptation and Proactive Failure Detection

Probabilistic Inference in Reinforcement Learning Done Right

Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient

From Large to Small Datasets: Size Generalization for Clustering Algorithm Selection

Learning Sequence Representations and Interpretable ML Models for Microbial Communities

Cross-validation for Geospatial Problems

Value-based Abstraction for Planning

Reinforcement Learning from a Bayesian Perspective

AI-in-the-loop for Health Care

Lipstick on a Pig: Using Language Models as Few Shot Learners

Integrated Planning and Reinforcement Learning for Compositional Domains

Planning and Learning for Reliable Autonomy in the Open World

Some Perspectives on Stochastic Gradient Learning and an Application to Neuroprosthesis

Great Haste Makes Great Waste: Exploiting and Attacking Efficient Deep Learning

The Data Pyramid for Generalist Agents

AI Can Learn from Data. But Can it Learn to Reason?

Data Science Consulting at AWS

Reinforcement Learning with Exogenous States and Rewards

Investigating Latent State and Uncertainty Representations in Reinforcement Learning

Vulnerability and Robustness of Linear Bandits

Show and tell us what you have accomplished since your last progress report (or since you started the project). Be open and honest!

Understanding Multiview and Self-supervised Learning: A Nonlinear Mixture Identification Perspective

Few Shot Object Segmentation

Probabilistic Planning through the Lens of Approximate Inference

Abstract The Center for Applied Systems and Software (CASS) is an experiential learning program for students. Our self-funded program provides hands-on learning for students on real world projects…

Human-AI Collaboration for Content Generation and Machine Autonomy