Lecture 21: Minimizing a Function Step by Step
MIT 18.065 Matrix Methods in Data Analysis, Signal Processing, and Machine Learning, Spring 2018 Instructor: Gilbert Strang View the complete course: https://ocw.mit.edu/18-065S18 YouTube Playlist: • MIT 18.065 Matrix Methods in Data Analysis... In this lecture, Professor Strang discusses optimization, the fundamental algorithm that goes into deep learning. Later in the lecture he reviews the structure of convolutional neural networks (CNN) used in analyzing visual imagery. License: Creative Commons BY-NC-SA More information at https://ocw.mit.edu/terms More courses at https://ocw.mit.edu

▶︎
22. Gradient Descent: Downhill to a Minimum

▶︎
Lecture 8: Norms of Vectors and Matrices

▶︎
Reinventing Entropy | Compression is Intelligence Part 1

▶︎
Training Sand to Think: Artificial General Intelligence & Future of Physics

▶︎
23. Accelerating Gradient Descent (Use Momentum)

▶︎
9. Four Ways to Solve Least Squares Problems

▶︎
Terence Tao: Nobody Understands Why AI Actually Works

▶︎
Terence Tao - 1/3 Bounded gaps between primes Download

▶︎
33. Neural Nets and the Learning Function

▶︎
Turing Award Winner: Disagreeing with Google, Postgres, Future Problems | Mike Stonebraker

▶︎
The most beautiful formula not enough people understand

▶︎
How Maxwell's Equations Were Discovered

▶︎
The Greatest Unsolved Problem In Mathematics

▶︎
Trump Sells UFC Coins as Iran Strikes & Melania Pushes AI in a Speech Worthy of AI | The Daily Show

▶︎
24. Linear Programming and Two-Person Games

▶︎
Lecture 10: Survey of Difficulties with Ax = b

▶︎
35. Finding Clusters in Graphs

▶︎
Intro to Gradient Descent || Optimizing High-Dimensional Equations

▶︎
