Letter #11 - In which we could please everyone, if only we tried harder.
“It doesn’t do any good at all to know that you can’t please everyone but not use that knowledge to be bolder, walk lighter and do better work for those you can please.”
There are lots of good reasons why researchers are so fixated on model architectures, but it does mean that there are very few resources available to guide people who are focused on deploying machine learning in production. (…)
As part of my job I work closely with a lot of researchers and product teams, and my belief in the power of data improvements comes from the massive gains I’ve seen them achieve when they concentrate on that side of their model building. The biggest barrier to using deep learning in most applications is getting high enough accuracy in the real world, and improving the training set is the fastest route I’ve seen to accuracy improvements.
The core idea being that once you have access to more (or better) data you will also be able to train more accurate models, even before starting to fine-tune the algorithms.
Cute small demo on using TensorFlow.js.
Not sure what you just read? Take a look at this post.
Enjoyed it? Subscribe to my tiny newsletter and get new issues straight to your inbox. Every week, on Tuesdays.