recentpopularlog in


« earlier   
Togelius: The differences between tinkering and research
I appreciate this. I generally find stuff that's tinkered with to be more approachable than stuff that's just good research. Maybe it's a matter of accessibility or not knowing the language of research well enough?
machinelearning  research 
yesterday by shurane
Lessons from My First Two Years of AI Research
Lot of tips on how to read papers, what conferences to follow, some researchers on Twitter, and a few other things. Seems great!
research  machinelearning 
yesterday by shurane
An Introduction to Hashing in the Era of Machine Learning
Bradfield blog updates on machine learning as applied to hashing (work by Google+MIT). Intro-level description of hashing, high-level description of machine learning, then an overview of the work and the results.

TLDR; machine learning models may help optimize larger indexes (like Google's BigTable) but a simpler algorithm (Cuckoo hashing) that can adapt to changes can be very efficient.

quote; "algorithms like cuckoo hashing remind us that machine learning is not a panacea"
databases  machinelearning 
yesterday by adamtait
GitHub - tkarras/progressive_growing_of_gans: Progressive Growing of GANs for Improved Quality, Stability, and Variation
We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality.
github  gan  machine  learning  machinelearning 
yesterday by peterb

Copy this bookmark:

to read