[romaniv]

I think it should be quite obvious that perceptrons are far from the smallest units that are capable of learning. They store many bytes of information, require a non-local update process, need numeric (i.e. symbolic) inputs and involve relatively complex computations. You can go much simpler. For example:

https://medium.com/@VictorBanev/the-simplest-learning-machin...

This is a description of a 5-line algorithm that learns and stores approximate probability of an event using just 1 byte of persistent memory.

[a1o]

That is a cool algorithm, indeed very interesting 5 lines. Also fun to see things in C#. :)

[DevarshRanpara]

True, there can be simpler versions compared to perceptron, just like you made. I have learned something new from that, Thanks for sharing.