The correct hyperparameter settings are critical to the success of a Feedforward Neural Network. In this video we take a high-level look on all main hyperparameters of Neural Networks. We see where in the lifecycle of the NNs they belong, what they mean and also how to set them using Python and Keras. 👇 Get your free AssemblyAI token here https://www.assemblyai.com/?utm_source=youtube&utm_medium=referral&utm_campaign=yt_mis_19 Intro 00:00 Input & output layers 01:01 Hidden layers 03:48 Activation functions 04:57 Weight initialization 06:34 Regularization 07:52 Loss functions 10:21 Optimization algorithm & learning rate 11:14 Batch size & Epochs (Number of iterations) 13:13 Wrap-up 16:12 Keras weight initializers: https://keras.io/api/layers/initializers/ Keras regularizers: https://keras.io/api/layers/regularizers/ Keras loss functions: https://keras.io/api/losses/ ▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬ 🖥️ Website: https://www.assemblyai.com/ 🐦 Twitter: https://twitter.com/AssemblyAI 🦾 Discord: https://discord.gg/Cd8MyVJAXd ▶️ Subscribe: null 🔥 We're hiring! Check our open roles: https://www.assemblyai.com/careers ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ #MachineLearning #DeepLearning