Deep learning (also known as deep structured learning, hierarchical learning or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and non-linear transformations.
https://github.com/arunsoman/deeplearning4all/wiki
Each of the above mentitioned stuff is an ocean in itself, but in a way these are simple; there are neurons which are stacked/connected to other neurons and each neuron has a property, when a neuron is triggred depending upon its property it may or maynot trigger other neuron. It gets intresting when a set of stacked neuron are connected to another set of stacked neurons.
I am no expert in this subject but I know experts have already provided some implementation & I can use them; This project is for those who wants to experiement with the neural networks without knowing the technicalities, api etc
planning something like this https://arunsoman.github.io/deeplearning4all/ui/index.html