Re:AlphaFold: a solution to a 50-year-old grand challenge in...
by ichbinwiederda on Monday November 30, 2020 @11:21AM
(#25255392)
Far from an expert on complexity theory, but NP-hard problems can be approximated in polynomial time. With Deep Learning you are doing approximation. So this is nothing ground breaking in that respect.
[ Parent
| on HN ]
Re:AlphaFold: a solution to a 50-year-old grand challenge in...
by foxtr0t on Monday November 30, 2020 @11:38AM
(#25255636)
That actually isn't totally true. Approximate methods, in the formal sense, require a guarantee that they perform within X of the optimal solution. Not all NP-hard problems have polynomial approximations and the methods shown here are likely not approximations because they very likely provide no guarantees on performance. They provide zero guarantees.
Re:AlphaFold: a solution to a 50-year-old grand challenge in...
by ichbinwiederda on Monday November 30, 2020 @11:50AM
(#25255809)
Yes thank you for elaborating. I agree with you on both counts.