Gradient Descent vs Newtons Method: Which ML Optimization To Use and Why
How do you train a model with millions of parameters? We decode the fundamental trade-off between Gradient Descent and Newton’s Method. Understand why deep learning relies on inexpensive first-order gradients (and why the incredible quadratic speed of second-order Newton methods becomes computationally impossible in high dimensions. References: 1. Deep Learning por Ian Goodfellow, Yoshua Bengio, y Aaron Courville 2. Numerical Optimization por Jorge Nocedal y Stephen J. Wright 3. Scientific Computing con MATLAB y Octave por Alfio Quarteroni, Fausto Saleri y Paola Gervasio

▶︎
The meme hiding surprisingly advanced math

▶︎
What's The Difference Between Matrices And Tensors?
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEnCNACELwBSFryq4qpAxkIARUAAAAAGAElAADIQj0AgKJDeAG4AvMY&rs=AOn4CLD_18b67Sqa4i4Yv09BD3B69fisZQ&usqp=CCY)
▶︎
Yann LeCun's $1B Bet Against LLMs [Part 1]

▶︎
The Integral Explained Better Than School Ever Did

▶︎
Terence Tao Explains The Math Behind AI

▶︎
Lagrangian vs Hamiltonian Mechanics

▶︎
Why Aliens Would NEVER Invade Africa

▶︎
The Strangest Things that Correlate with IQ

▶︎
The Man Who Trusted the Impossible — Bombelli's Wild Thought (1572)

▶︎
What does the second derivative actually do in math and physics?

▶︎
Feynman's technique is the greatest integration method of all time

▶︎
Co-Creator of Haskell: Functional Programming, Thinking in Types, Useless Languages | Simon Jones

▶︎
One second to find the BILLIONth PRIME

▶︎
When an audition changed TV forever

▶︎
Creator of C++: Bell Labs, Negative Overhead Abstraction, Mistakes | Bjarne Stroustrup

▶︎
How to Think So Clearly People Assume You’re A Genius

▶︎
The most beautiful formula not enough people understand

▶︎
Particle Life: simulating "life" with 200000+ particles

▶︎
Mathe-News! Durchbruch beim Kürzeste-Wege-Problem

▶︎
