A simple Neural Network implemented in Javascript without any framework.
URL: https://matheusr42.github.io/vanilla-js-neural-network/
You can read the comments in the code (main.js) and the references below to understand how it works.
-
Neural Network in Python with Numpy - Daniel Marostica: https://danielmkeras.medium.com/explicando-minha-rede-neural-programada-do-zero-7fbafa44e3b9
-
Course Deep Learning Specialization - DeepLearning AI: https://www.coursera.org/learn/neural-networks-deep-learning
-
Neural Networks Playlist - 3Blue1Brown: https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi
-
Activation Funcions: https://machinelearningmastery.com/choose-an-activation-function-for-deep-learning/#:~:text=for%20Output%20Layers-,Activation%20Functions,a%20layer%20of%20the%20network https://towardsdatascience.com/activation-functions-neural-networks-1cbd9f8d91d6
-
Learning Rate: https://towardsdatascience.com/understanding-learning-rates-and-how-it-improves-performance-in-deep-learning-d0d4059c1c10
-
Epoch vs Batch Size vs Iterations: https://towardsdatascience.com/epoch-vs-iterations-vs-batch-size-4dfb9c7ce9c9