HN user
This library originated from my need to handle 3D transformations, poses, trajectories, etc. from various software systems that often use different conventions. It has been developed for more than 7 years now and is in a fairly robust and well-tested state. It might be useful, for instance, in robotics, computer vision, motion capture, ...
Great! I sent an email.
Hi, that looks interesting. Where can I make a bug report? Can’t see the red button to start recording.
An Amazon review is not comparable to a review in a scientific journal. In a scientific journal a review is done by experts of the field and they invest a couple of hours / days. Scientists do this because it is part of their job. It is a contribution to the scientific community.
Maybe someone finds this interesting. This paper seems to be related: https://arxiv.org/abs/1907.04490
Same here. Those two books seem to be ordered only as pairs. ;)
Yes, you don't need to switch to a browser.
This reminds me a lot of the work on compressed neural network from Jan Koutnik and his colleagues. They don't evolve topology of a NN, but they learn weights of a neural network in some compressed space. That seems to be very similar to weight sharing.
Here are some related papers:
- original idea: http://people.idsia.ch/~tino/papers/koutnik.gecco10.pdf
- vision-based TORCS: http://repository.supsi.ch/4548/1/koutnik2013fdg.pdf
- backpropagation with compressed weights: http://www.informatik.uni-bremen.de/~afabisch/files/2013_NN_...
For example, in the case of the cart pole (without swing up) benchmark a simple linear controller with equal positive weights is required which can easily be encoded with this approach.
Overfitting is a well-known problem in the ML community. There are methods to avoid this: cross validation, train-test splits, etc. There are also models that give you an estimate of the standard deviation of a prediction. What is the point? We don't need new algorithms, we just have to apply existing methods properly.
I live in Germany and I would probably just go to the next hospital, wait for a while, get x-rayed and see a doctor. In this situation I wouldn't even have to think about money and I don't have to search for the best provider because they are all good. Even if I wouldn't go to a hospital, every doctor who can treat you usually can do an x-ray at his practice. I cannot imagine how it must feel in such a system in urgent cases. (edit: "such a system" refers to the American system)
There is Jodel: https://jodel-app.com/