1. Day 1 - How To Start (Almost) Any Project

   In this session, you'll learn how to pitch, sell, structure, and launch a new Machine Learning project. You'll find out how to frame complex problems in ways that set you up for successful solutions. Then, you'll cover how to run a discovery phase, address selection bias, manage data collection and labeling, and build an initial prototype.

2. Day 2 - How To Build A Model (That Works)

   In this session, you'll explore data cleaning and feature engineering, and learn how to preprocess data using vectorization, normalization, and imputation. Next, you'll cover strategies for selecting the best model for your problem and discuss how to iteratively build an end-to-end training pipeline. Finally, you'll walk through distributed training so you can scale your models with data and model parallelism.

3. Day 3 - How To Ensure Models Aren't Lying to Us

   In this session, you'll explore different evaluation strategies, such as cross-validation, LLM-as-a-judge, LLM juries, backtesting, invariance, and behavioral testing. Next, you'll see how to frame evaluation metrics in the context of business goals, ensuring your models work in real-world scenarios. Finally, you'll learn to prevent data leakages, perform error analysis, and handle imbalanced data.

4. Day 4 - How To Serve Model Predictions (In A Clever Way)

   In this session, you'll explore how to version and deploy models while dealing with key trade-offs and operational considerations. Next, you'll examine different strategies for serving predictions, including human-in-the-loop and cost-sensitive workflows. Finally, you'll learn about pruning, quantization, knowledge distillation, and Low-Rank Adaptation (LoRA) to compress and optimize models for real-world applications.

5. Day 5 - How To Monitor A Model (Drift Is Awful)

   In this session, you'll learn how to handle edge cases and outliers, address feedback loops, and detect and understand distribution shifts like covariate shift, label shift, and concept drift. Next, you'll see how to use adversarial validation and explore practical strategies for monitoring models in production. Finally, you'll explore different techniques to build resilient models that adapt to distribution shifts.

6. Day 6 - How To Build Continual Learning Systems

   In this session, you'll learn how to automate the entire process of building, deploying, and maintaining a model in production to create systems that learn and improve over time. You'll explore incremental training techniques, how to avoid catastrophic forgetting and different methods for retraining your models. Finally, you'll see how to test models in production using A/B testing, canary releases, shadow deployments, and interleaving experiments.

7. Code walkthroughs

   You'll get access to an end-to-end, production-ready template system for training, evaluating, deploying, and monitoring machine learning models.

   The codebase comes with extensive documentation to help you understand how the code works and how you could change it to accommodate your needs.

8. Office Hours

   Every week, we'll meet during office hours to answer any open questions, discuss relevant topics, and help you with any challenges you may be facing. This is also a great opportunity to connect with other students in your cohort, share insights, and talk about anything you are building or are passionate about.

Who Is This Program For?

This is hands-on program for people willing to put in the work to build skills with real-world impact.

This program is for software engineers, data scientists, data engineers, data analysts, machine learning engineers, technical managers, and anyone who wants to use Machine Learning and Artificial Intelligence to solve real-world problems.

Here are the prerequisites to succeed in the program:

• You are not afraid of writing code. We'll use Python, but you'll be fine if you have experience with any other language.
• You are familiar with basic machine learning terminology, like model training, evaluation metrics, and model inference. You don't have to be an expert, but this won't be an introductory class.
• You have a basic understanding of cloud services and how to build and deploy a simple API. Familiarity with Docker and containerization is not required but a helpful skill to have.
• You are ready to put in the work and commit the time necessary to succeed.

Upcoming Cohorts

Each iteration of the cohort consists of six live sessions plus office hours over three weeks.

Live sessions take place every Monday and Thursday. Office hours take place on Wednesdays. Every session is recorded. You can attend live or watch the recorded version later.

Here are the upcoming cohorts:

• Cohort 18: May 5 - May 22, 2025. 2:00 PM EDT
• Cohort 19: August 4 - August 21, 2025. 10:00 AM EDT
• Cohort 20: November 3 - November 20, 2025. 2:00 PM EST

Do not wait for a specific cohort to join the program. You have lifetime access, so you can join any time to lock in the current price.

Frequently Asked Questions

If you can't find the answer to your question, please reach out and I'll be happy to help.

How long will it take to complete the program?

Set aside a minimum of 4 hours every week during the three weeks of the program to attend the live sessions or watch the recordings. You'll need an additional 2 - 4 hours if you plan to go through the codebase.

What happens if I can't attend a live session?

Every live session is recorded. If you can't attend a live session, you can catch up asynchronously later using the recording.

I'm a complete beginner. Will this program be helpful for me?

This program is not an introduction to machine learning.

While we'll discuss many fundamental ideas behind machine learning, beginners will find the sessions go much faster than what's optimal for them.

What does "lifetime access" mean?

You only pay once to join the program and get immediate access to every past, present, and future cohort.

Every new iteration of the program is better than the ones before. Many students take classes once and then join a later cohort to benefit from the updates.

The lifetime access removes any pressure from having to complete the program when life gets in the way.