Hi folks!

I wanted to share a project I have been working on. It is a recurrent neural network that predicts bytes which can be used to mimic e.g. lyrical content (such as books). It uses Adams gradient optimization algorithm and the only requirement for using it is GCC. No third parties, just a bunch of C source files needed to be compiled. I have included some pretrained models that might be fun to play around with.

I hope this can serve as an inspiration to anyone wanting to make their own stuff “from scratch”.

Feel free to come with constructive comments on what I can add/change or any such requests. Have a great Monday!

Here is a link to the GitHub repository:

LSTM implementation (GitHub)

Don’t forget to give the repository a star if you like it, it would be really appreciated!