Taylor series: simplifying the complicated locally
Gradient descent actually assumes "it is flat from here on". We are going to measure exactly where that assumption breaks.
4 steps
170 XP
A free account is needed
Start the lesson →
Sources
- Nocedal, J. & Wright, S. J. 2006 · Numerical Optimization, 2. baskı, Bölüm 2 ve 3 · Springer
- Goodfellow, Bengio, Courville 2016 · Deep Learning, Bölüm 4.3 · MIT Press
- Boyd, S. & Vandenberghe, L. 2004 · Convex Optimization, Bölüm 9.5 · Cambridge University Press
ML Academy · an interactive machine learning course that runs in your browser ·
All lessons