Building Feedback Loops for Continuous Improvement
Was this section helpful?
Machine Learning Engineering, Huyen Chip, 2019 (Chip Huyen) - Comprehensive guide to ML system design, deployment, monitoring, and maintenance, with emphasis on practical aspects of MLOps and feedback loops.
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback, Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, Jackson Kernion, Tom Conerly, Sheer El-Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, Scott Johnston, Shauna Kravec, Liane Lovitt, Neel Nanda, Catherine Olsson, Dario Amodei, Tom Brown, Jack Clark, Sam McCandlish, Chris Olah, Ben Mann, Jared Kaplan, 2022arXiv preprintDOI: 10.48550/arXiv.2204.05862 - Describes a method for training large language models using human feedback to improve their helpfulness and harmlessness, demonstrating a direct application of feedback loops in LLM alignment.
MLOps: Continuous delivery and automation for machine learning on Google Cloud, Karl Weinwurm, Eric Schmidt, Hamel Husain, Dale Markowitz, Sarah Nusser, Nick O'Leary, Evan Schwartz, Pete Warden, Danny Hernan, Noah Treuhaft, 2024 (Google Cloud) - Provides best practices and architectural guidance for MLOps, including how continuous integration, delivery, and training leverage feedback loops for iterative model improvement.