The Stanford AI Lab Blog

OCTOBER 13, 2021

Across a range of applications from vision 1 2 3 and NLP 4 5 , even simple selective classifiers, relying only on model logits, routinely and often dramatically improve accuracy by abstaining. As a motivating example, consider the task of diagnosing pleural effusion, or fluid in the lungs, from chest X-rays.

Neural Network 40

Neural Network Machine Learning Computational Linguistics Deep Learning 40

Unite.AI

JUNE 15, 2023

Originally from Canada, Deon enjoys spending time with his wife and son, playing basketball, and reading as many books as he can get his hands on. Originally from Canada, Deon enjoys spending time with his wife and son, playing basketball, and reading as many books as he can get his hands on. Could you summarize what Forethought is?

Large Language Models 246

Large Language Models Generative AI Chatbots Auto-complete 246

The MLOps Blog

MARCH 21, 2023

As the number of ML-powered apps and services grows, it gets overwhelming for data scientists and ML engineers to build and deploy models at scale. As the number of ML-powered apps and services grows, it gets overwhelming for data scientists and ML engineers to build and deploy models at scale. That’s where this guide comes in!

Machine Learning 69

Machine Learning Data Scientist ML Metadata 69