Applying Active Learning in Drug Discovery - There's No Free Lunch, but You Can Get a Discount
Explore active learning applications in drug discovery, from prioritizing molecules for synthesis to virtual screening of large libraries, with insights on machine learning's impact across the process.
Corporate Social Responsibility via Multi-Armed Bandits
Explore how multi-armed bandit algorithms can be applied to corporate social responsibility, balancing profit maximization with societal impact in decision-making processes.
Collaborative Top Distribution Identifications with Limited Interaction
Explore collaborative learning strategies for efficient multi-armed bandit problem-solving, focusing on top-m identifications with limited interactions and error reduction techniques.
Inside TensorFlow - TF-Agents
Explore TF-Agents, TensorFlow's reinforcement learning library, with experts demonstrating its capabilities, architecture, and applications in game playing, bandits, and recommender systems.
Productionizing ML Models for Online Shopping at Loblaws
Explore ML model productionization for online shopping, covering microservices, CI pipelines, AB testing, and cloud-based implementation using tools like Seldon Core.
Continuous-in-time Limit for Bandits
Explore the connection between Hamilton-Jacobi-Bellman equations and multi-armed bandit problems, and discover an efficient algorithm for solving MAB challenges.
Adversarially Robust Stochastic Multi-Armed Bandits
Explore adversarially robust stochastic multi-armed bandits for optimal experimental design. Learn about algorithms balancing fast and robust learning in real-world applications like digital advertising.
Adversarial Machine Learning: Beyond Manipulating Pixels and Words
Explore vulnerabilities in sequential machine learning and challenge assumptions about imperceptible attacks on image classification through human behavioral studies.
Introduction to Artificial Intelligence - Bandit Algorithms - Lecture 15
Explore bandit algorithms in AI, learning key concepts and applications for modern problem-solving in gaming environments.
Information-Directed Sampling for AI Agent Alignment - From Theory to Practice
Explore Stanford's groundbreaking Information-Directed Sampling approach for aligning AI agents with human values, focusing on optimal decision-making and continuous learning in dynamic environments.