Artificial Neural Networks "learn" to perform tasks by considering examples. They do this without any prior knowledge. Instead, they automatically generate identifying characteristics from the examples that they process. Beside the success of an AI model the confusion or error matrix is an important tool. It gives a risk profile we have to deal with when using AI models.
How good is good enough? How wrong is still an acceptable level? The confusion or error matrix is an important tool. It gives a risk profile we have to deal with when using AI models. It's exactly the same tool that is often used for the evaluation of medical interventions.
Evaluating the appropriate parameters of a model is the core of every machine learning algorithm. In neural networks such a procedure has to be repeated over an over. Beceause of the non-linearities numerical approaches which approximate the solution iteratively are an important class of solution.
We go through the basic steps of machine learning using the most elementary models, linear and logistic regression namely. This gives a first outlook on the machine learning proces.