00:00First, you should understand that an artificial neural network is, at its core, a mathematical equation

00:04A powerful neural network is typically a very complex equation, but nevertheless, it's just math

00:10Like in the brain, we connect multiple neurons together and form a neural network, which we can train to perform a task

00:16So, how do these artificial neurons work? Well, the essence of an artificial neuron is nothing but this simple equation from elementary school, where X is the input, W is a weight, B is a bias term, and the result, our output, is Z of X

00:31What does this mean? Essentially, any input X is being modified by multiplying with a weight, and then a bias is added in order to get a result or output

00:40This allows the AI system to map the input

00:43value X to some preferred output value Z of X

00:46How are W and B determined? This is where training

00:51We have to train the parameters W and B into the AI system such that the input can be modified into the appropriate or correct output.