
This course includes our updated coding exercises so you can practice your skills as you learn.
See a demo
I hope to give you all the high level touch points as well as demo assignments to help guide you on your journey as an machine learning engineer.
Define the roles and responsibilities of a machine learning engineer. Explore two buckets: technical work, including big data, building and shipping models, and people work across teams, leadership, and adoption.
This is an optional and informal tangent lecture on some common applications of machine learning at various companies.
After this lecture, you should have a better grasp of the common applications of machine learning and where you can find a job in ML.
Explore exploratory data analysis and use python notebooks to analyze simple and complex datasets with pandas, matplotlib, and seaborn, applying an NBA basketball data example to reveal insights and questions.
Discover the power of pandas and access official and unofficial resources, tutorials, and help from ChatGPT to support your practical machine learning practice.
Explore the etl pipeline—extract, transform, and load—and migrate notebook code to etl form while creating a hello world data workflow for the second assignment, noting prefect over airflow.
Train diverse ml models using scikit learn and XGBoost, compare classification and regression, explore supervised vs unsupervised learning, apply Shap values for explainability, and evaluate with appropriate metrics.
We'll cover some aspects about PyTorch and demo a tutorial to showcase some of the advantages of the PyTorch framework. You'll be better equipped to venture out and try out one of the many official tutorials that PyTorch offers.
Understand what ML in production entails, from live fraud decisions and deploying models to production, to observability, online versus offline inference, feature stores, and Kubeflow-driven orchestration.
Explore ml observability with evaluation metrics including accuracy, precision, mae, and mse, plus business metrics like conversion rate and dollars saved, AB testing, and data drift detection.
Hope you had fun and learned something new! I have linked some additional resources that may be useful in your learning journey.
This course is designed for learners from all backgrounds, primarily focusing on beginners.
The course covers many of the cornerstones of practical machine learning, including:
Industry Use Cases and Employer Expectations: Explore a variety of industry applications for machine learning and understand what companies are looking for in ML roles.
Exploring Real-World Data: Gain hands-on experience with data sourced from a real-world scenario, learning to navigate and interpret complex datasets.
Building Data Workflows: Understand the architecture of data pipelines, including typical tools and techniques used in the industry.
Model Development and Evaluation: Learn how to construct machine learning models and critically assess their performance and effectiveness. Iterate upon models with feature engineering and hyperparameter tuning.
Model Deployment and Monitoring: Master the skills necessary to deploy models into a production environment and continuously monitor their performance.
Value to Learners:
Applicability of Skills: The skills taught are directly transferable to real-world scenarios, equipping learners with the tools needed for a career in machine learning.
Comprehensive Understanding: From data handling to model deployment, this course offers a holistic view of what it takes to be a machine learning engineer.
Hands-On Experience: With a focus on practical exercises and real-world examples, learners will gain firsthand experience that goes beyond theoretical knowledge.