It is frustrating trying to learn about machine learning. Do I use YOLO, Keras, Tensorflow, PyTorch or all of them together somehow? And even if you figure out the PhD stuff, you still have to then master about three other disciplines to get it to work in production; devops, programming, and counting disciplines.

Well I am here for you brothers and sisters in computers, I have good news for your peace of mind.

The most important thing in getting machine learning to work properly is training data.

And even more importantly, the skills required to make a good training set have nothing to do with math, computers, or engineering.

What is training data?

Let’s say you need a machine learning model to tag e-mails as spam when they come in. In order to train that model, you need training data. In this particular example, a good training set might consist of 1000 examples of spam e-mails and 1000 examples of not-spam e-mails (or ham as I’ve sometimes heard it called).

The tools to take that data and turn it into a machine learning model that works exist today and are easy to use. You don’t have to go Berkeley to use them, you just have to be a little familiar with computers.

#ai & machine learning #data #data science #machine learning #training