screwlisp

https://lispy-gopher-show.itch.io/dl-roc-lisp/devlog/1465107/shark-restaurant-dl-roc-dot-lisp-explained-deep-learning-receiver-operating-characteristic-part-2-simple-version

#itchio #gamedev #programming #theory completely explainable game-embeddable #deepLearning system using #roc #statistics .

I coded this one simply and iteratively, since a few people worked on reimplementing my #commonLisp code to-be-simpler.

The gist is that I show that deep learning updates, and indicate training as well are a simple true-positive/true-negative/false-positive-false-negative equation of the previous time step in an eminently explorable way. #DL #AI

Mar 21 at 6:15amWeb
Show threadscrewlisp1d ago

cc @thuna @etenil if you want to update your system, since this one explains what being a multilayer deep learning neural networks is as well at the end, which I know you were working on.

Just the git: https://codeberg.org/screwlisp/dl-roc.lisp

dl-roc.lisp

Deep learning receiver operating charateristic formulation pure ansi common lisp conditions. This formulation is original to me and is a fully explainable general trainable, inferenceable deep learning model in the conventional one- or multi-layer ffnn way.

Codeberg.org