It’s not my aim to explain how Artificial Intelligence works and I never tried to, just sometimes I’ve discussed the media approach on the topic.
I’ve seen this video and it explains quite well how the core of this technology works. We are speaking about back-propagation neural network, the pattern recognition engine that works at the core of r.Virgeel and that makes the magic.
My first experiments with neural networks were back in the early 90s using Brainmaker. It was not 4 minutes, but in maybe half an our you could have a quite complex network running. Then training time was hours. In 2013 it took me three years to build the spxbot.com model and it’s under continuous development. Large part of the work really stands in maintaining the data base, formed by tables that have hundreds of fields and thousands of records that must be aligned and updated, always. Without exception. Now the network size has reached the remarkable dimension of a maximum over twenty millions of neurons. It is not the positronic brain, yet. It is just a single complex table that offers the possibility to correlate a large number of inputs and some experimental training ideas for the output side.