Visual and intuitive overview of the Gradient Descent algorithm. This simple algorithm is the backbone of most machine learning applications.
——————-
References:
– AI plays hide and seek: https://openai.com/blog/emergent-tool-use/
– AI plays Dota 2: https://openai.com/five/
– InterFaceGAN: https://www.youtube.com/watch?v=uoftpl3Bj6w
– Boyd and Vandenberghe’s book on Convex Optimization (Sections 9.2 and 9.3): https://web.stanford.edu/class/ee364a/lectures/unconstrained.pdf
https://web.stanford.edu/~boyd/cvxbook/bv_cvxbook.pdf
——————
Timestamps:
– 0:00 Intro
– 0:18 Problem Formulation
– 1:10 Gradient Descent
– 2:12 Flavors of Gradient Descent
——————-
Music: www.bensound.com
This video would not have been possible without the help of Gökçe Dayanıklı.
Add comment