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
Random weights have often been a surprisingly strong baseline. Back in 2007-2011 we often saw convolutional nets with random weights getting state of the art performance on object recognition tasks like CalTech-101 and CIFAR-10
Feature extraction via projection on a large family of random filters. Works especially well if your weights have an orthogonal initialization (so you don't lose to much information in the process).
Yes, thanks! Another friend also referred us to the Johnson-Lindenstrauss lemma in random projections. Would your expectation be that projection on a large family of random filters would work as well as a random fixed CNN, both with the same output dimension?
I'd expect the random CNN to work better. Would be an interesting experiment.
I was going to add a tweet but it didn't go through. What's interesting here is not that a random network would work, it's that training this random network does not improve its performance. It's a sign there's a fundamental flaw with how we think about the setup.
If random projections work at all, it should be very easy to tune these random projections to get a better network. No reason to believe the random weights were a local minimum.
orthogonal projection makes prefer sense. You may look for directions close to whatever, possible, rotation and reflection. @abursuc the paper that you recently posted.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
