<html> <p>When you think of technical education about machine learning, Facebook might not be the company that pops into your head. However, the company uses machine learning, and they’ve rolled out <a href=„https://research.fb.com/the-facebook-field-guide-to-machine-learning-video-series/“ target=„_blank“>a six-part video series</a> that they say “shares best real-world practices and provides practical tips about how to apply machine-learning capabilities to real-world problems.”</p> <p>The videos correspond to what they say are the six aspects of machine learning development:</p> <ol><li>Problem definition</li> <li>Data</li> <li>Evaluation</li> <li>Features</li> <li>Model</li> <li>Experimentation</li> </ol><p>None of the videos are longer than 10 minutes, so you’ll invest less than an hour. The videos focus less on a specific product and more on the architecture and implementation strategies. That’s valuable, but this probably isn’t your only machine learning tutorial.</p> <p>Quite a bit of these videos cover things we think are pretty obvious engineering axioms applied to machine learning. For example, a recurring theme is that you need to have a way to evaluate the system and do testing to see that things you change are actually making things better. Still, there are some things that are specific to machine learning.</p> <p>Facebook has been in the news a lot lately, mostly not in a good way.  However, their research arm quietly turns out things ranging from Torch — a scientific computing framework with machine learning, to speech recognition and synthesis.</p> <p>It seems like a lot of companies want to teach you about machine learning, <a href=„https://hackaday.com/2018/05/22/machine-learning-crash-course-from-google/“>including Google</a>. You can even run <a href=„https://hackaday.com/2018/04/16/tensorflow-in-your-browser/“>TensorFlow in your browser</a>.</p> </html>