Code of the paper "Beyond calibration: estimating the grouping loss of modern neural networks" published in ICLR 2023.

DSPy: The framework for programming—not prompting—foundation models

Investment Research for Everyone, Everywhere.

An alternative implementation for an imagined handwriting decoder

A playbook for systematically maximizing the performance of deep learning models.

Cookiecutter python package using Poetry, mypy, black, isort, autoflake, pytest, mkdocs, and GitHub Actions

AI and Machine Learning with Kubeflow, Amazon EKS, and SageMaker