The artificial intelligence (AI) platforms of today are largely based on a technology known as artificial neural networks. These neural networks mimic the way that the human brain works. They consist of neurons which takes some inputs and fires a signal to the next neuron if the inputs pass some threshold value. This diagram shows a sample neural network used to classify handwritten numbers. The nodes are arranged in layers with the output of one layer becoming the input to the next layer until the final output layer is reached. The diagram shows a neural network that has been trained to recognise handwritten numbers recognising the number 3.

Image source: IEEE Spectrum Oct 2021