Explore a keynote presentation from the Haskell 2023 conference that delves into the intersection of Haskell programming and choice-based machine learning. Discover how combining algebraic effects, handlers, and the selection monad can create powerful languages for decision-making models and optimization-driven techniques. Learn about a prototype Haskell library implementation and examine programming examples for stochastic gradient descent, hyperparameter tuning, generative adversarial networks, and reinforcement learning. Gain insights into the potential of Haskell for advancing machine learning programming paradigms, presented by Ningning Xie from Google DeepMind and the University of Toronto.
Overview
Syllabus
[Haskell'23] Haskell for choice-based learning
Taught by
ACM SIGPLAN
Related Courses
-
Artificial Intelligence: Reinforcement Learning in Python
-
AI skills for Engineers: Supervised Machine Learning
-
Effect Handlers for Choice-Based Learning in Machine Learning Programming
-
Insights on Gradient-Based Algorithms in High-Dimensional Learning
-
Large Scale Machine Learning and Convex Optimization - Lecture 1
-
Reinforcement Learning in Recommender Systems - Some Challenges
