Human-in-the-Loop Mixup: Aligning Synthetic Data with Human Perception - Oral Session 2
Explore human-aligned synthetic data in machine learning, focusing on mixup regularization. Discover how perceptual judgments and uncertainties can enhance model reliability and generalization.
Probabilistic Circuits That Know What They Don't Know - UAI Oral Session 6
Explore probabilistic circuits' robustness to out-of-distribution data and learn about tractable dropout inference for improved uncertainty quantification in a single forward pass.
Diversity Measures: Domain-Independent Proxies for Failure in Language Model Queries
Explore domain-independent diversity measures to detect uncertainty in language model outputs, enhancing error detection and improving AI reliability.
Leveraging Latent Representations for Predictive Physics-Based Modeling
Explore advanced techniques for leveraging latent representations in predictive physics-based modeling, focusing on surrogate models, inverse problems, and transfer learning for complex PDEs.
Derivative-Informed Neural Operators for Solving PDE-Governed Optimization Problems
Explore novel machine learning for solving optimization problems with PDEs, featuring derivative-informed neural operators for efficient, scalable solutions in high-dimensional parameter spaces.
How Could We Design Aligned and Provably Safe AI?
Explore AI safety with Dr. Yoshua Bengio, focusing on run-time risk evaluation and Bayesian approaches to mitigate potential harm from advanced AI systems.
Inference and Uncertainty Quantification for Noisy Matrix Completion - Lecture 5
Explore inference and uncertainty quantification for noisy matrix completion, focusing on de-biased estimators and their distributional characterizations for optimal confidence interval construction.
Probabilistic Richardson Extrapolation
Explore probabilistic Richardson extrapolation using Gaussian processes for accelerated convergence in numerical methods, with applications in cardiac modeling and statistical experimental design.
Uncertainty Quantification in Machine Learning: Federated Conformal Prediction
Explore uncertainty quantification in machine learning through federated conformal prediction, enhancing model reliability and decision-making in distributed settings.
Robust Design Discovery and Exploration in Bayesian Optimization
Explore data-driven methods for robust design discovery and optimization, focusing on Bayesian techniques that efficiently handle uncertainties and adversarial scenarios in various scientific domains.
High-Dimensional Prediction for Sequential Decision Making
Explore efficient algorithms for online high-dimensional predictions, enabling no-regret guarantees, fairness, and uncertainty quantification in multiclass settings for improved decision-making.
The Materials Simulation Toolkit for Machine Learning (MAST-ML): Automating Development and Evaluation of Machine Learning Models for Materials Property Prediction
Automate machine learning model development for materials property prediction using MAST-ML. Learn data import, feature engineering, model evaluation, and uncertainty quantification through hands-on activities.
Explainable and Robust AI for VILMA Virtual Laboratory
Explore explainable AI and uncertainty quantification in atmospheric research. Learn about SLISEMAP, a supervised manifold visualization method for local explanations and dimensionality reduction.
Probabilistic Programming Tutorial - Part 2
Explore advanced concepts in probabilistic programming, focusing on practical applications and techniques for scientific computing and data analysis.
Uncertainty Quantification with Conformal Prediction - A Path to Reliable ML Models
Dive into conformal prediction techniques for quantifying uncertainty in ML models, covering implementation across various domains and practical applications using Python and pre-trained neural networks.
Probabilistic Machine Learning - Lecture 19
Dive into advanced data science concepts through comprehensive lecture coverage of key theoretical and practical aspects in this graduate-level academic session.
Big Data Inverse Problems - Promoting Sparsity and Learning to Regularize
Explore novel methods for solving big data inverse problems, focusing on sparse representation and L1 regularization. Learn about variable projection and deep neural networks for parameter optimization.
ML-driven Models for Material Microstructure and Mechanical Behavior - DDPS
Explore ML-driven approaches for generating microstructures and accelerating material behavior analysis. Learn transfer learning techniques and rapid assessment methods for materials design optimization.
Data-Driven Modeling of Unknown Systems with Deep Neural Networks
Explore data-driven modeling of unknown systems using deep neural networks. Learn to discover and approximate evolution operators for predictive analysis across various problem domains.
Physics-Enhanced Gaussian Processes for Learning of Electromechanical Systems
Explore physics-enhanced Gaussian processes for modeling electromechanical systems. Learn about GP-PHS and physics-enhanced variational autoencoders to improve data efficiency and ensure physical correctness.
Challenges and Opportunities for Integrating Physics-Knowledge in Machine Learning Strategies
Explore integrating physics knowledge into machine learning algorithms for improved generalization and physics-consistent predictions. Examine biases and strategies through a friction identification case study.