In my opinion, this whole thing is a regular exercise in technological marketing
1. Write about some seemingly powerful tech that creates fear (AI, nuclear, quantum, etc). Fear creates engagement.
2. Do a PR campaign where journalists write clickbaity headlines on a subject they are incapable of explaining, let alone understanding.
3. Try to enhance your brand by showing you are achieving some success on a hard problem.
Google desperately needed to do this because they are losing the AI narrative, so they have a strong incentive to do a coordinated PR stunt.
Undoubtedly the greatest athletic achievement and honor I will ever have in my life. I have no words to describe the feelings I have right now but I do know I am currently filled with gratefulness and thankfulness ❤️ love you guys thank you.
Good advice! For classification models, a scatter plot of the cross-entropy loss vs. prediction entropy (~confidence) for individual examples can be very revealing.
More generally: study model behaviour for individual data points, don't look at aggregate statistics exclusively.
Looking forward to doing a tutorial on Causal Inference, Experimental Design and Reinforcement Learning at #NeuRIPS2020!! For a list of all tutorials, see https://t.co/Ta7LX95kRZ
Jupiter is looking sexy in a new Hubble photoshoot. Turbulent but beautiful. The red spot is a giant storm larger than Earth. Also, photobombing is Europa, a moon that is likely to have liquid water under its icy surface, and therefore might also have extraterrestrial life.
As requested , here are a few non-exhaustive resources I'd recommend for getting started with Graph Neural Nets (GNNs), depending on what flavour of learning suits you best.
Covering blogs, talks, deep-dives, feeds, data, repositories, books and university courses! A thread 👇
“When I am at my best, I know it is because of what I learned from my dad about respecting women, honoring individuality, and guiding children’s choices with love and respect.”
“Entanglement” is full of meaning in physics, but the linear algebra behind it is quite simple. Ever used SVD? Then you're nearly there! Today on Math3ma, I'm discussing “Schmidt rank” in hopes of helping the math feel a little less... tangly. New post!
https://t.co/zJytgj7VSy
Machine learning courses that I highly recommend:
"Scalable and Flexible Models of Uncertainty" by @RogerGrosse : https://t.co/ETcLQjtDLE
"Learning to Search" by @DavidDuvenaud : https://t.co/SBbpPJuMYj
"Data-Driven Algorithm Design" by @yisongyue : https://t.co/jwdPjhfcQw