This paper makes the points that it's the saddles and not local minima that are the problem: https://arxiv.org/abs/1406.2572 It was the basis for adding 'momentum' to optimizers - so that you could skate across the…
...hmm, that was counter to my understanding (limited though it may be...) which was partially formed by this paper: https://arxiv.org/abs/1712.09913 TLDR - loss landscapes are nasty, but you can tame them with skip…
...sounds like it costs much more than the $10 pi0... I imagine the OP's use case of IoT did not require huge amounts of bandwidth.
Ahem...trebuchets are superior to catapults in every way.
Not sure I would call a New York Times article 'clickbait'...
This paper makes the points that it's the saddles and not local minima that are the problem: https://arxiv.org/abs/1406.2572 It was the basis for adding 'momentum' to optimizers - so that you could skate across the…
...hmm, that was counter to my understanding (limited though it may be...) which was partially formed by this paper: https://arxiv.org/abs/1712.09913 TLDR - loss landscapes are nasty, but you can tame them with skip…
...sounds like it costs much more than the $10 pi0... I imagine the OP's use case of IoT did not require huge amounts of bandwidth.
Ahem...trebuchets are superior to catapults in every way.
Not sure I would call a New York Times article 'clickbait'...