Towards Safe and Efficient Learning in the Physical World - Stanford Seminar
Exploring safe Bayesian optimization and model-based deep reinforcement learning for efficient, safe online learning in real-world applications like robotics and laser tuning.
Machine Learning for Personalized Healthcare - Opportunities, Challenges and Insights
Explore machine learning's impact on personalized healthcare, from disease subtyping to tailored interventions, with insights on mental health, respiratory diseases, and critical care settings.
Towards Generalization of Precise Robot Skills - Accurate Pick-and-Place of Novel Objects
Explore precise robotic generalization for pick-and-place tasks using simulation-learned models. Discover how visuo-tactile sensing enables accurate object manipulation and placement with sub-millimeter precision for novel items.
A Probabilistic Approach for Situation Awareness and Forecasting of COVID-19 in Norway
Explore a probabilistic model for regional COVID-19 transmission using mobile data and epidemiological time series, with insights on its practical application in Norway's pandemic management.
See to Act, Act to See - The Interdependence of Planning and Perception in Robotics
Explore the interdependence of planning and perception in robotics, focusing on physical property learning, multi-modal sensing, and uncertainty modeling for improved task performance.
Learning Real-World Probabilistic Models with Approximate Message Passing
Explore probabilistic modeling for big data using factor graphs and message passing. Learn how Amazon tackles real-world problems with advanced statistical techniques in the era of structured data.
From Large to Infinite Random Simplicial Complexes
Explore two models of random simplicial complexes extending the Erdos-Renyi model, examining their Alexander duality relation and the unique infinite Rado simplicial complex.
Nonparametric Bayesian Methods - Models, Algorithms, and Applications IV
Explore probabilistic models for graphs, edge exchangeability, and graph paintbox representations in this advanced machine learning lecture on nonparametric Bayesian methods.
Statistical Models: Linking Data to Theory - Class 1
Explore statistical models in ecology, linking data to theory. Learn logistic growth, ecological studies, and probabilistic modeling techniques for quantitative analysis.
Diffusion Models Beat GANs on Image Synthesis - Machine Learning Research Paper Explained
Explore how Diffusion Models outperform GANs in image synthesis, with improved architecture, classifier guidance, and better sample quality while maintaining distribution coverage.
Neural Nets for NLP 2020 - Search-Based Structured Prediction
Learn search-based structured prediction techniques for NLP, including structured perceptron, max-margin objectives, and exposure bias remedies. Explore global models and cost-augmented training for improved sequence prediction.
Diffusion Models - Google Colab Experimentation with Code and Prebuilt Models - Part 2
Hands-on exploration of Diffusion Models using Google Colab, covering probabilistic implementations and prebuilt models. Includes code examples and practical demonstrations of the denoising process.
Joint Embedding Method and Latent Variable Energy Based Models
Explore joint embedding methods and latent variable energy-based models with Yann LeCun. Learn about predictive systems, inference, probabilistic models, and various training techniques for advanced machine learning applications.
Energy Based Models and Self-Supervised Learning
Explore energy-based models, latent variables, and self-supervised learning. Dive into EBM training, inference, and comparison with probabilistic models. Discover contrastive methods and applications like K-means and BERT.
Machine Learning: From ABCs to DEFs
Explore machine learning fundamentals, from basic concepts to practical applications, focusing on people, data, and code. Learn to build simple AI models and understand key ML principles.
Spin Systems with Hyperbolic Symmetry
Explore spin systems with hyperbolic symmetry, their origins, applications in probabilistic models, recent findings, and open questions in this advanced mathematical discussion.
Probabilistic Models for Learning a Semantic Parser Lexicon
Probabilistic models for learning semantic parser lexicons from question/answer pairs, improving accuracy and efficiency without extensive human input or dataset-specific engineering.
Marginal Determinism in Structured Decomposable Circuits
Explores marginal determinism in probabilistic circuits, introducing md-vtrees for structured decomposable PCs. Discusses tractability conditions, efficient algorithms, and applications to causal inference queries like backdoor adjustment.
The Rise of Tractable Circuits - From Cryptography to Continuous Generative Models
Exploring tractable circuits' applications in cryptography and continuous generative models, showcasing advancements in neuro-symbolic approaches and probabilistic inference for AI reasoning.
Solving Marginal MAP Exactly by Probabilistic Circuit Transformations
Efficient marginal MAP solver for probabilistic circuits using iterative transformations and pruning, enabling exact solutions without search for decision-making problems.
Data is as Data Does - The Influence of Computation on Inference
Exploring the impact of computational approximations on probabilistic models in machine learning, with focus on Gaussian Process approximations and their applications in neurobiology.