cool_username

Not looking to do work for you, just a tip. Look into ZFS. Daily snapshot, incremental etc? No problem.

However something you'll need to think about if you're snapshotting - do you need to snapshot the memory state/disk buffers too? e.g. a database. Or anything where the total state of the VM is split between disk and CPU/memory.

If the answer is no this is an easy problem to solve.

If the answer is 'yes' life gets more complicated.

we can predict the result of a neutron star collision and be right

To be fair, what we're predicting happened long ago in the past... predictions about the past are always easier :)

What I find puzzling is that this pink chocolate 'invented in 2017 by a Swiss company marketing to millenials' appears to have been available in British sweet shops for over 20 years.

https://www.sweetsncandy.co.uk/a-jar-of-pink-and-white-choco...

https://i.pinimg.com/originals/66/0b/87/660b8713654b075c0a81...

My conclusion: while the Swiss are masters of chocolate, the Brits are masters of time travel.

I agree that this and the 'adversarial road signs' work indicate a growing interest in security attacks on ML.

https://medium.com/self-driving-cars/adversarial-traffic-sig...

However, in this case, it's not just machine learning. It will affect non-ML audio-processing systems just as much.

I would add to the list, but I can't login to my account at the moment since I don't have my bespoke HSBC 2FA physical device (despite having a far-superior, non-polluting equivalent on my phone...)

If someone banks and does 2FA on the same phone, if the phone gets hacked (malicious app) you have a big problem on your hands.

Out of curiosity, do you genuinely believe there is a citation out there relating to the treatment of chickens on this farm today vs. treatment of chickens on 10000 small household farms 100 years ago?

It comes across as though you are demanding impossible standards of evidence here in order to cut off a side of an argument you don't agree with, and don't want to begin to consider?

"Citation needed" is not a universally acceptable reflexive alternative to discussion of things you don't personally agree with.

Having a dozen chicken in a large yard seems to me to be pretty nice for the chicken.

Citation needed.

That's generally helpful and usually enough, but it's not universally helpful, depending on the shape of the problem and your step size - see Figure 5 below.

(http://graemebell.net/pubs/taros05-bl-embedded-preprint.pdf)

It also depends what the impact of 'perturbations' is in the real world.

Random juddering motions can be bad for physical platforms like robots, spacecraft.

[I once saw a conference presentation where people were encountering saddle point problems when automatically aligning groups tiny space craft in space]

In computer games, random perturbations can make movement look strange, unrealistic or creepy.

Assuming you want to understand a bit more about saddle points:

http://graemebell.net/pubs/taros05-bl-embedded-preprint.pdf

Section 3 has some low dimensional examples with simulated robots and donkeys.

Take a look at Figure 3 with the donkey.

Burridan's Ass is a classic philosophical example where a saddle point prevents success.

Basically, place a donkey between two piles of food in front of it that are equally attractive. The donkey moves in whatever direction will take it towards food.

So at first, it can move forward (reducing its distance to both piles of food) up to a point, but then it gets stuck because both piles are equally attractive. It can't move forward or back either because that moves it away from both piles of food.

There is nothing to 'push' the donkey to the left or the right.

('push'/hunger being analogous to 'following the gradient' for neural net training or robot navigation here)

If you add a bit of a random wobble, it's enough to free the donkey from its indecision and make one of the piles slightly closer.

But things are more complex than that especially as you move into higher-dimensions of space beyond 2D and 3D [as you see when training neural nets, for example].

And a random wobble is not enough to guarantee success. It may have consequences for physical devices (your robot shakes around and falls over), it may have consequences for realism and immersion in games/simulations (the AI monster stops and does a mad shake for a minute to creep its way around a rock to get you, rather than moving smoothly/normally around the rock)

Our sharp rate depends on a key observation — although we don’t know the shape of the stuck region, we know it is very thin.

Oh... really? :)

(After 12 years I finally get an excuse to show a fun side project I coauthored during my PhD...)

http://graemebell.net/pubs/taros05-bl-embedded-preprint.pdf

Check out Figure 5 / Section 3.4

The rest of the paper is an introduction to why saddle points can be surprisingly problematic for people using potential fields (neural nets, game/robot navigation). Hope someone finds it interesting.