But what is cross-entropy? | Compression is Intelligence Part 2

Where the loss function for training LLMs comes from. If you want to learn more about Lagrange Multipliers, I made multiple videos and articles for the topic back in my Khan Academy days: Manim animations by Aaron Gostein and Grant Sanderson NanoGPT animation by Clayton Rabideau 3d black-box model...

Beginner - 34 min - AI & Data - 3Blue1Brown

The full course: Learn Math for ML free

What you'll need

• Laptop stand: Screen at eye level for long study sessions.
• Noise-cancelling headphones: Focus through long video lessons.
• Second monitor: Video on one screen, practice on the other.
• Wireless keyboard and mouse: Comfortable for hours of typing.

Books

1. Mathematics for Machine Learning by Marc Peter Deisenroth - View on Amazon
2. Naked Statistics by Charles J. Wheelan - View on Amazon
3. Practical Statistics for Data Scientists by Peter Bruce - View on Amazon
4. The Art of Statistics by David Spiegelhalter - View on Amazon
5. The Elements of Statistical Learning by Trevor Hastie - View on Amazon

Next lessons

• But what is a convolution? (23 min, 3Blue1Brown, Beginner)
• But what is the Fourier Transform? A visual introduction. (20 min, 3Blue1Brown, Beginner)
• How (and why) to take a logarithm of an image (45 min, 3Blue1Brown, Intermediate)
• Simulating an epidemic (23 min, 3Blue1Brown, Intermediate)
• But what are Hamming codes? The origin of error correction (20 min, 3Blue1Brown, Intermediate)
• Divergence and curl: The language of Maxwell's equations, fluid flow, and more (16 min, 3Blue1Brown, Intermediate)
• Solving Wordle using information theory (31 min, 3Blue1Brown, Intermediate)
• Taylor series | Chapter 11, Essence of calculus (22 min, 3Blue1Brown, Intermediate)