Medijski sadržaj
- Tweetovi
- Tweetovi i odgovori
- Medijski sadržaj, trenutna stranica.
-
source https://www.youtube.com/watch?v=uUzHeaDU4NM … The whole speech is amazing to watch.
Prikaži ovu nit -
Infrastructure work can be tiring and demanding but it is very important to do so that interesting questions can be asked or answered. Apollo astronaut armstrong had a very funny way to put it.pic.twitter.com/VWFpl6z0ph
Prikaži ovu nit -
-
They do a series of experiments to highlight the accuracy of this 6D representation. source code in pytorch is here: https://github.com/papagina/RotationContinuity …pic.twitter.com/2FJzv26frl
Prikaži ovu nit -
Quaternions and Euler angles are discontinuous and difficult for neural networks to learn. They show 3D rotations have continuous representations in 5D and 6D, which are more suitable for learning. i.e. regress two vectors and apply Graham-Schmidt (GS). https://arxiv.org/abs/1812.07035 pic.twitter.com/fXUF3sgkTT
Prikaži ovu nit -
It still amazes me that someone came up with such a crazy way of landing a space shuttle. This is a nice insightful and hilarious video explaining how they used to land a space shuttle.https://www.youtube.com/watch?v=Jb4prVsXkZU …
Prikaži ovu nit -
Interestingly they also try Pareto optimal multi-task learning for their problem.pic.twitter.com/jTVXQee2p8
Prikaži ovu nit -
They combine a robust (shift and scale invariant) function that compares prediction against ground truth together with another loss function that penalises the gradients.pic.twitter.com/HZR0smabRO
Prikaži ovu nit -
Impressive results on single image depth estimation by Ranftl et al https://arxiv.org/abs/1907.01341 pic.twitter.com/f6nrhXyCCH
Prikaži ovu nit -
If you plug t = 1/pi in the last two equations you arrive at the result. This one extends from the Basel problem also used to obtain the identity that sum of inverse squares up to infinity = pi^2/6 source: https://en.wikipedia.org/wiki/Basel_problem …pic.twitter.com/8fYHdZ1lEh
-
I saved it from a long video here https://www.youtube.com/watch?v=uUzHeaDU4NM … I knew this was such a gem that it would be worth sharing in future.
-
-
This is a nice short tutorial on normalising flows by
@ari_seffhttps://www.youtube.com/watch?v=i7LjDvsLWCg … -
This is for procedurally generated terrains (I found it on HN) https://s-macke.github.io/VoxelSpace/VoxelSpace.html …pic.twitter.com/IBBqzJlg8Y
-
So, the trick is that since alpha is also a part of normalising constant (Z) you have to also estimate that so that you can compute the derivatives otherwise the loss function collapses. Without the Z it doesn't work.pic.twitter.com/b4MSr4Sulm
-
Robust functions are useful in regression because they can cull the outliers from the optimisation process. Since the alpha is a free parameter they can learn that.pic.twitter.com/GjRnhNLcs2
Prikaži ovu nit -
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
