Classical Machine Learning

Machine Learning (ML) initially started in the '50s and '60s as pattern recognition. They got better by seeing more data. Most of these algorithms were based on statistics and probabilistic reasoning, by measuring the distance between data points, directions of vectors, intensities of values, etc. These [old] algorithms are widespread. You can see them everywhere -- read this article next, Google reporting your random sign-in -- they're simple to use, easy to understand, and don't require a large amount of computational power.