Generating consciousness

One week ago I wrote this post about an insight on what could "consciousness" be like, and I imagined it as something not-so hard to gasp as we always thought. Today I come back with a "pseudo-code" version of it on my mind.

Those new ideas have come along with an effort in our company to port the fractal algorithm into a distributed, highly scalable architecture. A work in progress that is already producing a great speed-up in our tests.

This new architecture allows me to play with big groups of fractals diseminated over a network of PCs, all doing the same decision work in paralell, to later join all their findings and take a "collegiated" decision.

More interestingly, I can now "pack" some fractals to work as one big fractal and replicate it endlessly to build a tree of cooperating fractals as a nice way to distribute work over the PCs on the network.

But how to arrange them to distribute the work even more efficiently? By building it as a "fractal of fractals", a tree of fractals whose structure evolves dynamically as you use it, to finally form a nice tree-like fractal that adapts its form to live in the environment you gave to it.

What is Consciousness?

Some days ago I wrote a little about how this fractal AI works, it was not too detailed and the really important details were intentionally left unsolved. I promise to fill the gaps in short for you to be able to try the fractals by your self, but not now.

Today I want to give an overview of how the "complete fractal AI algorithm" could look like in some months, the ideas I am actually working on, and specially some random thoughts about consciousness.

The part I am now working at is about how to add memory to the fractal AI. This far, fractal AI was totally memory-less, meaning it does not learn from experience at all. I now call this an pure instinct-drive or intuitive mind. When you ask something to this AI, it thinks on the problem from scratch, and gives you an answer that is good enough for evolving in this medium with intelligence, a "real time " decision making algorithm good enough for many task.

But while driving a rocket on a difficult environment is hard but can be done with just an intuitive fractal AI, most NP-hard problems -problems where the time needed to solve it grows exponentially with the size of the problem to be solved- are usually not so easy to solve just with pure intelligence, usually you need something more to guide the intuition.

Pathfinding problem

In my first contact with professor Talbi he proposed me to try to solve the Pathfinding general problem with my algorithms, as the examples I showed in my talk were quite similar to solving it.

The Pathfinding problem consist in finding the shortest path from point A to B and it is useful not only in programming robots to go here and there, many other problem relates to finding this path.

So I borrowed time here and there to prepare a couple of videos and yesterday I have a second meeting with him to show the videos along with the real-time example where the agent follows the mouse. Here you have the video I prepared for the meeting:

 

Paretto frontiers

Last Thursday professor El-Ghazali Talbi from Lille University hold a talk about metaheuristic classification and his unified framework ParadisEO to deal with it on the Elx University Miguel Hernandez CIO, and after the talk (I enjoyed it a lot and learn things a was supposed to already know and some more!) I had a little time to explain my latest fractal methods and show some of the videos I had been producing about them.

There was some debate after the talks about the classification itself and the Pareto frontier way of working on multi objective optimisation problems.

Basically, actual approaches try to maximise all the functions at the same time, if possible, and if not, then obtain the optimum solution for any weighted combination of those functions, so for any possible combination you get a point, and all those points form the "Pareto Frontier" of the problem.

Understanding the mining example

My friend Samuel (@Samuel__GP) suggested me -in a comment- to try to explain how simple the idea used is compared with the rich an efficient behaviours it produces on the rocket, and it is not easy, but I will try...

So first have a look at this video:

The goal of the player is to pick up rocks with it's hook and then take them to the deploy area (the small circle filled with a grid). Once the rock is there, the hook releases and you can not trap the rock again until it leaves the big circle. In that moment, the rocket will try to catch it again and so on.

Entropic AI using Excel

Some days ago, Raul Perez (@raulperezrpm) kindly contacted me on twitter to comment about my first talk on entropic intelligence, and just two days later, I received a video from him of the entropic algorithm working inside Excel macros!

Emotional links

Adaptive foraging, or the ability to harvest and collect items, is the main test-bed for swarm intelligences, as it resemble real life problems and mimic interesting social behaviours like ants and bees swarms.

So I am adapting my fractal AI code to deal with this problem, and as a first result, here I show you a video with only one agent (quite a small swarm!) so I can test if the new gadgets works OK.

The rocket now have a hook that will trap asteroids as a magnet. The hook is connected to the rocket with a rubber band, making the rocket-hook structure quite difficult to manage.

Are maths the real languaje of nature?

I have just had a vision random thought I wanted to share before going to bed: What if mathematics were not the real basement of real world physics? What if the laws of nature are not really physicals laws written in pure maths as we all have naively assumed? Can physics be rethink in a absolutely different way?

I think there exists a way to describe all known physics without using any mathematical formula, a way to describe what a "wave equation" really is without using mathematically defined fields of any kind, just using algorithmics, in fact using just a single, small and compact algorithm.

Folding proteins with a fractal

Yesterday I posted about the fractal algorithm adapted to function optimising, the test I showed was nice, but dealing with a 2D function is not so great if you plan to go big.

After that Guillem forgot to go home and stayed coding a little more at the office. This morning the algorithm was able to load test proteins and try to fold them by minimising the Lennard-Jones potential of the cluster. He sleept in the sofa!

Here you see it folding a 5 atoms "protein":

Serious fractal optimizing

Guillem Duran, my friend and college from twitter, is now full-time at work with me at converting the "one way" fractal algorithm used in my latest AI into a "serious" general optimising algorithm in python: given a function, find its global (as opposed to local) maximum -or minimum- value it can get on its entire domain -the points on the state space where the function is defined.

Last week we finished the conversion, so we are just starting to benchmark it against other "state of the art" similar algorithms, but to have a first view of the you have a preliminar video here: