Geek Girl Joy

Artificial Intelligence, Simulations & Software



Scaling Data

Size is relative and statements like “too big” or “too small” (cough TWSS 😛 ) are not immutable properties of the universe but rather simply a matter of perspective. Change your perspective just a little Goldilocks and you might find that your neural network thinks your data porridge tastes “just right”!

Err… what I mean is… we’re going to look at how to scale your data so that you can feed it to your neural network without causing it (or you) to have any unpleasant indigestion.

Specifically, lets say you have a very important series of values (including strings of text) that you want to use as part of your training dataset but they don’t fit within the yummy-data range of -1 to 1… so what do you do?

Continue reading “Scaling Data”

A Spooky Turing Test

Welcome to A Spooky Turing Test!

I first wrote about my Writer Bot October 31’st 2017 in the post A Halloween Tale.

That post was written by the absolute BEST writer bot at the time (created by yours truly) though I haven’t released the code for that version of the bot and sadly it has been surpassed (barely) in capability (for now) by a bot called GPT2 created by “OpenAI“.

So, I’ve decided to use GPT2 instead of Writer Bot for this post

If you are looking for spooky posts written by me I’d suggest reading my encounter with the Polybius VR Virus (be careful what you download) or if you want something more recent checkout A Spooky Real Neat Blog Award, it’s a bit of a horror tall tales variety act.

If you want a bit more math and a little scifi with your spooky story you might be interested in the “Mysterious Game of Life” series that is part of my Ancestor Simulations posts.

And if you just want the wallpaper for this post, here you go:

A Spooky Turing Test Wallpaper
A Spooky Turing Test Wallpaper

Otherwise let me attach this last electrode to GPT2 and we’ll be ready to proceed with a Spooky Turing Test.

Continue reading “A Spooky Turing Test”

Training a Visual Bot

By the end of this post you will have everything you need to train your own visual neural network!

Previous posts in this series:

Continue reading “Training a Visual Bot”

Generating Visual Training Data

Today we’re going to look at how to automatically generate training data from images.

At the end of this post I publish the working code (copy->paste->run) that you can use commercially in your own projects for free…  oh and I explain how it works, need I say more? 😉

Other posts in this series:

Continue reading “Generating Visual Training Data”

Building a Visual Bot

Today we’re going to look at the code used to build a visual neural network but don’t worry… there will be pretty pictures and I’ll keep the math to a simplified minimum. 😛

Continue reading “Building a Visual Bot”

Introduction to Creating Visual Neural Networks

In last week’s post The Kiss I teased:

“In my next post we’ll “feed” this image to a neural network.”

This Image

The Kiss
The Kiss

I guess now its time to make good on that promise… so lets do that, shall we?

Continue reading “Introduction to Creating Visual Neural Networks”

How I Built A Working AutoDoc

Ever been a lone wanderer solely surviving in the Commonwealth Wasteland only to have some random asshole raider start taking potshots at you? Well I have!

To make matters worse Bon Jovi showed up out of nowhere at the most inopportune moment  seemingly just to mock my hasty strategic withdrawal!

I used my last stimpak as I staggered through the door of my Red Rocket workshop where Dogmeat and Codsworth were waiting for me.

I changed then ate some ramen, Takahashi always makes the best pulled noodles!

I stared into the radstorm raging outside my window and in that moment I vowed:

Never again would Bon Jovi mock my pain!”


I needed to build a new kind of bot and this time “General Atomics Finest” just wouldn’t cut it!

No, I needed a neural network that could monitor my vitals and automatically heal me as soon as I started taking damage!

Continue reading “How I Built A Working AutoDoc”

Visualizing Your FANN Neural Network

At some point you will want a diagram of your FANN neural network.

Example Diagram

Programmatically generated diagram of XOR ANN
Programmatically generated diagram of XOR ANN
Programmatically generated XOR ANN Stats
Programmatically generated XOR ANN Stats

Reasons May Include:

  • You need artwork for your fridge or cubical and Van Gogh’s Starry Night was mysteriously unavailable!
  • You want an illustration to help potential investors understand some of the technical aspects of how your AI startup works.
  • You’re trying to convince the good people who enjoy your work to throw gobs of cash at your Patreon. 😛

But.. Your exact reasons may very! 😉

None the less, read on because I’m giving you 100% free & fully functional code and explaining how it works.

I’m not even asking for your email address!


Continue reading “Visualizing Your FANN Neural Network”

How to take Training Snapshots of your PHP FANN Neural Network

Today we’re going to look at how to take snapshots of your FANN Artificial Neural Network  (ANN) while it’s training.

But why?

Well, maybe you want to fork competing GANs to progressively create ever increasingly  believable deepfakes because you want some of that sweet, sweet deepfake money… um… I mean, build a best seller Writer Bot… 😉 😛

Perhaps you want to compare how different processes, configurations or algorithms affect your ANN during training rather than waiting till the end.

Or… maybe, you have a pug and toddler who conspire to take turns crawling under your desk and push the power switch on the surge protector ~60 hours into a long and complex training process and you’d rather not lose days of work… again!

OK… not a third time smarty pants! 😛

Continue reading “How to take Training Snapshots of your PHP FANN Neural Network”

Create a free website or blog at

Up ↑

%d bloggers like this: