Tipousi - a tiny and fast deep learning framework from scratch in C++

This is a WIP project that implements an entire deep learning framework from scratch in C++.
The goal is to implement as many layers and modules as possible and have a python interface at the end.
This will probably take some time but it would help me understand the tiny details behind many concepts.
Currently the project builds a shared library (e.g., libTipousi.so) (that will hopefully be distributed and used with python at some point) and a tests executable TTests.

Include externals (submodules)

git submodule init
git submodule update

TODOs

• implement more stuff...

• focus of backward pass implementation

• add enum for initial weights distribution

• allow for multiple inputs/outputs to sequential