Adaptive Gradient (AdaGrad) | Parameter Specific Optimization | Vanishing Learning Rate Problem
About this lesson
๐ Notes: https://robosathi.com/docs/deep_learning/optimization-method/#adagrad ๐ฅ NLP Course: https://www.youtube.com/playlist?list=PLnpa6KP2ZQxcDlHCeNiKbRhLWKVunQaxn ๐ฅ Deep Learning Course: https://www.youtube.com/playlist?list=PLnpa6KP2ZQxe749nPGDV2cd6SR6zIZIJl ๐ฅ Machine Learning Course: https://www.youtube.com/playlist?list=PLnpa6KP2ZQxeydAqz2lsSMFYinbrJy9mu ๐ฅ Full Maths Course: https://www.youtube.com/playlist?list=PLnpa6KP2ZQxen-R6NytSMigAri7piPhFp Pre-Requisites: ๐ฅ Optimization Methods Video: https://youtu.be/-q5IZkJT3nE ๐ Time Stamp ๐ 00:00:00 - 00:00:33 Introduction 00:00:34 - 00:02:28 Problem with Sparse Features 00:02:29 - 00:05:20 Adaptive Gradient Algorithm 00:05:21 - 00:07:30 Adaptive Gradient Detailed Explanation 00:07:31 - 00:08:38 Vanishing Learning Rate Problem 00:08:39 - 00:09:04 Next: RMSProp
DeepCamp AI