Researchers at Stanford University explore Direct Preference Optimization (DPO) in machine learning. Uncover the hidden biases in machine learning with a look at historical bias. Understand the bridging gap between correlation and causation with Causal AI. Discover a new AI method that captures uncertainty in medical images. Stay informed about the latest advancements in machine learning and their implications for various industries.
Sources:
https://www.marktechpost.com/2024/04/20/researchers-at-stanford-university-explore-direct-preference-optimization-dpo-a-new-frontier-in-machine-learning-and-human-feedback/
https://towardsdatascience.com/un-objective-machines-a-look-at-historical-bias-in-machine-learning-da5101d46169
https://www.marktechpost.com/2024/04/20/understanding-causal-ai-bridging-the-gap-between-correlation-and-causation/
https://news.mit.edu/2024/new-ai-method-captures-uncertainty-medical-images-0411
Outline:
(00:00:00) Introduction
(00:00:40) Researchers at Stanford University Explore Direct Preference Optimization (DPO): A New Frontier in Machine Learning and Human Feedback
(00:03:26) (Un)Objective Machines: A Look at Historical Bias in Machine Learning
(00:07:08) Understanding Causal AI: Bridging the Gap Between Correlation and Causation
(00:10:35) New AI method captures uncertainty in medical images
view more