You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
The ML research community has long been driven by the need to publish, which results in a stark, sometimes ridiculous bias towards complexity. Remember to ask: "can we do this with k-means and logistic regression?"
Can we do super-resolution with k-means & logreg? Probably Can we do generative models (structured latent space from which on can sample high-res images) with interpolated patches with k-means & logreg? Probably Pixel-to-actions on Atari games with k-means & logreg? Probably Etc
Can we do 83% accuracy on CIFAR10 with k-means and logistic regression? Yes (Coates 2011).
I think we should have a "simple, strong baselines" workshop at major ML conferences. This would help focus ML research on real progress.
That is so true…
Is that not like saying, I can get different levels of accuracy by taking the first, second or third terms of a Taylor expansion? Who cares if a simpler method gets a decent approximation?
The person paying tha AWS bills cares a lot
.
Agreed, except for the k-means part. It fails in far too many cases
Yes, but there are really very simple improvements to K-means that can solve most of the problems with it e.g.:http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0162259 …
I think in many cases the complexity of the approach or its formulation is so great that reviewers totally overlook poor / mediocre results!
This is something which needed to be said
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
