Super Data Science: ML & AI Podcast with Jon Krohn 474: The Machine Learning House
May 28, 2021
Discover the blueprint of a 'machine learning house' and how foundational topics like linear algebra, calculus, and probability form the bedrock of a successful data science career. Explore how mastering these subjects can deepen your understanding of machine learning. Learn effective strategies for progressive learning, including practical coding tools and concepts to elevate your skills. This engaging discussion provides valuable insights for anyone aspiring to thrive in the data science field!
AI Snips
Chapters
Transcript
Episode notes
Start High-Level, Then Go Deep
- Start with high-level code like Scikit-Learn and Keras to get a feel for real-world applications.
- Once you feel limited, delve into foundational subjects like linear algebra and calculus.
Go Beyond Abstractions
- Outstanding data scientists need more than just surface-level knowledge of libraries like Scikit-Learn.
- Deep understanding of machine learning theory is crucial for innovative models and efficient deployment.
Who Should Focus on Foundations
- If you use high-level libraries and want deeper understanding, study foundational subjects.
- This also benefits software engineers and data engineers deploying models.