Understanding the bleeding-edge GAN papers from one of the world's best known AI research conferences. Some musings on the academic workshops on "applied ML".
All ICML GANs / Generative Papers: I went to Stockholm and spoke to academics, so you don't have to! Domain adaptation, 3D GANs, Data Inputation using GANs and much more!
As it often happens, I get busy at work and forget to publish something I should have really done months ago. Well, this code is that thing. But at least it's now nice and shiny.
I know what you're thinking: can there be anything more exciting? Rest assured, the wild party don't stop there. So hold on to your glasses nerds, we're going to do some A-friggin-I. Or if you're into ML and think this minus the sarcasm. But actually, this is super cool.
AI is moving forward at an amazing rate but we should take the time to appreciate all the amazing potential of the recent advancements. I want to take the time to get some technical appreciation for the business implications the recent AI may have.
My trip to the <1% of data scientists. Or in the the world of competitive data science and back again. Aka: three (relative) successes and a fail. Also how not to spend a lot of money on your data problem. I need to start writing better summaries.
I said I will stop at finishing 14 online courses... and I am doing three MOOCs again. Review of my learning journey, projects I have done, reviews of great and good courses, my (brief) take on practices. UPDATED.
Slightly technical, but relatively simple introduction to randomness and why it has to be everywhere around us. (Also check out the cool new LaTeX plug-in.)
Exploring the power of Big Data approach (GDELT) applied to the civil war in Syria to get unconventional insights into the Syrian civil war and the terror tactics of ISIS.
Quick and dirty statistical modeling in R for social scientists, decision makers and enthusiasts. Insights from my involvement in a US intelligence project.
I have just returned from ICLR 2019 in New Orleans and what a fruitful year that was on GAN papers-we saw papers on image synthesis (BigGAN), audio (WaveGAN), feature selection (KnockoffGAN), 3
In all seriousness, however, I do respect greatly all the amazing work that the researchers at ICML have presented. I would not be capable of anywhere near their level of work so kudos to them