100 Days of Deep Learning - Nesterov Accelerated Gradient (NAG) Explained in Detail | Animations | Optimizers in Deep Learning

The acceleration of momentum can overshoot the minima at the bottom of basins or valleys. Nesterov momentum is an extension of momentum that involves calculating the decaying moving average of the gradients of projected positions in the search space rather than the actual positions themselves. This has the effect of harnessing the accelerating benefits of momentum whilst allowing the search to slow down when approaching the optima and reduce the likelihood of missing or overshooting it. Notes: https://learnwith.campusx.in/s/store/courses/YouTube%20Notes ============================ Do you want to learn from me? Check my affordable mentorship program at : https://learnwith.campusx.in ============================ 📱 Grow with us: CampusX' LinkedIn: https://www.linkedin.com/company/campusx-official CampusX on Instagram for daily tips: https://www.instagram.com/campusx.official My LinkedIn: https://www.linkedin.com/in/nitish-singh-03412789 Discord: https://discord.gg/PsWu8R87Z8 ⌚Time Stamps⌚ 00:00 - Intro 00:47 - What is NAG? 09:12 - Mathematical Intuition of NAG 12:52 - Momentum 17:59 - Geometric Intuition of NAG 24:39 - Disadvantages - (1) 25:55 - KERAS Code Implementation 27:30 - Outro