With which option! I have used Colab myself and I don't see live editing. I would like to see the cursor of the collaborators in real time while they edit. Also, the option to share the runtime.
Not necessarily, it depends on the advisor, university, program and field.
The problem is that once you start you are committed for 4 years. Abandoning a PhD program and starting another one is quite more complicated than changing of job.
It's not only about the odds, but the expected return. That's the whole point of insurance, for instance. Having an accident under these circumstances is quite improbable, but in case it happened, the return would be massive. Actually, since it might be a matter of life or death, perhaps it doesn't even make sense to think about the expected utility, because it would be infinite.
This is the kind of ad-hoc PEP proposal that could be completely avoidable if there was a generic modifier or initialization/declaration construction for declaring a variable as constant. So incredibly simple, so incredibly useful that it's hard to believe that it hasn't been accepted yet (it was proposed).
When I was in college I was mystified by genetic algorithms, without knowing much about them. After taking 2 subjects on the matter and reading some books, I came to the conclusion that apart from being inherently inefficient (that's what you apply them when you have no alternative), they are actually outperformed by hill climbing (which can be seen as a particular case of the former if population = 1). Also, the crossover operator seems to make more harm than good, and it's not fully understood it's usefulness in nature, although there are some theories (this last point is taken from Pedro Domingos book).
I know, but isn't that what the OP was asking for? Isn't that an inherent tradeoff? Or: isn't that what Neuromorphic hardware and deep learning are about (ie. composing many relatively simple functions without complex branching/logic)?
Contrary to the belief of progressive billionaires, I think the reform of capitalism will come in form of local "soft socialism". Localism just makes sense and can be accepted by both left and right-wing people.
Pytorch is amazing and Facebook's open source contributions to AI are great.
However, tooling for deep learning in general is not ready for industry grade technology. Many bugs could be prevented by dependent types, but compilers are not there. Also, debugging models feels like alchemy and random changes until it works. In addition, in production systems, rigorous testing is not a standard. The closest thing I have heard of is Tesla's data engine and AI system, they do have unit tests and a shadow mode. Of course big companies will have similar technologies for critical systems, but it's not as standardized as testing in software engineering.