The core of Artificial Intelligence
I must have started this page before the hype in AI really started to take off.
Now that Anthropic have announced that their new AI is too powerfull to release to the general public the topic has come back into focus. I must admit that looking at this again there is a large measure of "Jargon Soup".
Also looking at how Trump is involved in AI and the Middle East I came across the concept of the AI Stack
Backpropogation and Machine Learning
Backpropogation is the term used by those that claim to the experts in A.I. that describes the control process (algorithm) that is used in Machine Learning.
All the hype around AI is going to change the world and that it should be legislated before it gets out of hand means that it seems to be constantly in the News (February 2026). Sadly, those that report on it have no clue on what it is all about. I don't either! but I am trying to work it out.
In machine learning, backpropagation is a gradient computation method commonly used for training a neural network in computing parameter updates.
It is an efficient application of the chain rule to neural networks. Backpropagation efficiently computes the gradient of the loss with respect to the network weights for a single input–output example. It does this by propagating derivatives backward, one layer at a time, from the output layer to the input layer, thereby avoiding redundant chain-rule calculations.
Top
Neural Networks
Wikipedia again:
In machine learning, an artificial neural network is a mathematical model used to approximate nonlinear functions. Artificial neural networks are used to solve artificial intelligence problems.
