In this tutorial, we show how we treat prompts as first-class, versioned artifacts and apply rigorous regression testing to large language model behavior using MLflow. We design an evaluation pipeline ...

Abstract: The paper considers automated methods of cardiac diagnostics with a preliminary conclusion about cardiac arrhythmias in a patient. The importance of this task stems from insufficient ...

This project focuses on building a custom neural network framework from scratch for multi-class and binary-class classification tasks, as well as regression. The purpose of the project is primarily ...

Bayesian linear regression with automatic guide construction, dual inference engines (SVI and MCMC), and posterior predictive analysis using Pyro. Without this workflow, you would need to manually ...