In the rapidly evolving world of technology, machine learning has emerged as a foundation, driving innovation and efficiency across industries. Santiago Valdarrama, an experienced machine learning engineer and YouTube content creator from the channel Underfitted, offers a comprehensive roadmap for those wanting to dive into this dynamic field. With over 20 years of experience working with industry giants such as Disney, Boston Dynamics, IBM, and Dell, Valdarrama provides a clear and structured path for aspiring machine learning professionals.
Building a strong foundation
The path to machine learning begins with a solid understanding of Python, the programming language that dominates the field. “Start with Python,” advises Valdarrama. “All scientific research papers are written in Python, all the libraries are in Python, it's the language that the AI community uses to communicate.” He recommends Udacity's Intermediate Python program for those with some prior knowledge, and says that there are plenty of free tutorials online for complete beginners.
Understanding Python is not a one-check-and-done thing, but a continuous learning process. Valdarrama emphasizes, “I started learning Python after 20 years of coding in other languages, and I still feel like I'm just scratching the surface.”
Immersive Learning with Kaggle and Google
Once you're comfortable with Python, Valdarrama recommends diving into machine learning with Kaggle tutorials. These tutorials are concise, beginner-friendly, and provide a gentle introduction to basic machine learning concepts. “Kaggle's 'Introduction to Machine Learning' tutorial is a great starting point,” he notes. Subsequent 'Intermediate Machine Learning' tutorials provide further insight and practical experience.
The next step is the Google Machine Learning Crash Course, a comprehensive program consisting of 25 lessons spread over 15 hours. Originally designed to upskill Google's own team, the course is free to take and provides a solid intermediate-level education in machine learning.
Advanced Learning: Coursera Specializations
For those ready to tackle more advanced topics, Valdarrama recommends Coursera's Machine Learning Specialization. This paid course requires a monthly subscription, but offers in-depth knowledge and practical experience with more complex machine learning algorithms and mathematical concepts. “This specialization is a great bridge to advanced machine learning because it's more formal and includes rigorous math,” Valdarrama explains.
Take advantage of university classes
Top universities, including MIT, NYU, and Cornell, offer free machine learning and deep learning courses online, and Valdarrama encourages students to take advantage of these resources, citing MIT 6.S191 Introduction to Deep Learning and NYU's Deep Learning course as great options.
Must-read
Valdarrama also shares some recommended books for those looking to become machine learning experts.
- Practical Machine Learning with Scikit-Learn, Keras, and TensorFlow Author: Aurélien Géron: This book provides a comprehensive overview, from basic decision trees to advanced neural networks.
- Deep Learning with Python Author: François Chollet: Written by the creator of Keras, this book walks you through the entire process of a deep learning project, from data collection to deployment.
- Machine Learning with PyTorch and Scikit-Learn Author: Sebastian Raschka: This book focuses on PyTorch, another essential tool for machine learning engineers.
For those interested in building applications using generative AI and large-scale language models, Valdarrama offers the following recommendations: Generative AI with LangChainLearn about using AI APIs and building AI workflows.
Practical tips for learning
Valdarrama emphasizes the importance of solving real-world problems to effectively learn machine learning. He recommends that beginners start with popular datasets like the Titanic or MNIST datasets to gain practical experience. “Tackle problems that 10,000+ people have already worked on,” he says. “That way, you'll find plenty of resources and solutions to help you when you get stuck.”
Knowledge sharing is another important aspect of learning. Valdarrama encourages learners to find outlets to explain what they've learned through blogs, social media, or video content. “Teaching others helps solidify your understanding,” he explains.
Follow your curiosity
Machine learning is a vast field that encompasses areas such as computer vision, natural language processing, and time series analysis. Valdarrama advises students to explore broadly and then focus on areas that truly interest them. “Pursue what makes you happy,” he says. “You're more likely to become an expert in one area than if you try to master everything at once.”
Valdarrama believes that with patience and perseverance, a career in machine learning is within reach, and his roadmap, filled with practical advice and plenty of resources, offers a clear path for those ready to embark on this exciting journey into the future of technology.
