Limits of Learning
The conversation delves into the essence of deep learning, highlighting that its effectiveness hinges on the presence of underlying rules within data. If data is purely random, there's nothing for the computer to uncover, leading to a dead end in scientific discovery. The interplay between theory and application in mathematics is also explored, revealing a shared excitement for both realms as they seek to unveil the hidden signals in our world.In this clip
From this podcast
Lex Fridman Podcast
Gilbert Strang: Linear Algebra, Teaching, and MIT OpenCourseWare | Lex Fridman Podcast #52
Related Questions