"This is just a small ode to the folks who spend countless hours on the toil that is 'just' getting some labelled data."
Read it!"In online machine learning, the idea is that your model is only allowed to learn from one example at a time. This is contrast to batch learning where all the available data is processed at once."
Read it!"The difficulty is that machine learning is a fundamentally hard debugging problem. Debugging for machine learning happens in two cases: 1) your algorithm doesn't work or 2) your algorithm doesn't work well enough."
Read it!