Activation Function | Why Non Linearity is important in Deep Learning ? | Sigmoid | ReLU | Softmax
About this lesson
๐ Notes: https://robosathi.com/docs/deep_learning/activation-function/ 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: ๐ Differentiation Notes: https://robosathi.com/docs/maths/calculus/calculus-fundamentals/ ๐ฅ Differentiation Video: https://www.youtube.com/watch?v=Vw35N4zDF-I ๐ Time Stamp ๐ 00:00:00 - 00:00:30 Introduction 00:00:31 - 00:01:25 Why do we Need Activation Function ? 00:01:26 - 00:03:35 Why is Non Linearity Important ? 00:03:36 - 00:04:45 Universal Approximation Theorem 00:04:46 - 00:08:10 What will happen If we Do Not Use Activation Function ? 00:08:11 - 00:09:01 Common Activation Functions 00:09:02 - 00:12:43 Sigmoid Activation Function 00:12:44 - 00:14:50 Hyperbolic Tangent (TanH) Activation Function 00:14:51 - 00:18:20 ReLU Activation Function 00:18:21 - 00:20:02 Leaky ReLU Activation Function 00:20:03 - 00:22:56 Softmax Activation Function 00:22:57 - 00:25:09 Softmax Example 00:25:10 - 00:25:53 Next: Optimization Methods
DeepCamp AI