# Is it possible to learn to estimate the minimum value in a table?

Is it possible to classify or learn to estimate the minimum value in a table if the values are integer and represented 32 bits (and we can input all variables at the same moment, like in system on a chip (SoC))?

• I'm not sure what you're asking. To find the minimum in a list, you have to look at every element once, and the simple solution (a for loop scanning the table) is a theoretically optimal O(n). If you get to design circuitry that can read every input at once, you can get that down to O(1) time, though the cost in terms of silicon and complexity would be formidable. Or something like O(log n) pretty simply. In any case, I'm not sure what you're hoping for from a learning algorithm. Can you elaborate? Dec 27 '17 at 14:51
• @mico why is that ? Dec 27 '17 at 14:54
• @deong you absolutly right, but to answer your question i was looking for resolve a minimum search problem as a learning problem, and try to design a parallel solution just to figure out if any problem can be considered a learning problem Dec 27 '17 at 15:00
• I know there has been a lot of work on things like learning parallel sorting algorithms, for example. I've seen some work on genetic algorithms for that I know. That might provide you a starting place to jump off from. Dec 28 '17 at 16:15
• I think a learning technique could be used if the allocation of numbers in that table are determined by a method each value can be said to be determined by another. The algorithm would be employed to determine this method and subsequently the contents of the table. If the table is populated by random means I don't think no amount of learning could be employed to achieve it since there's no knowledge determining its allocation.
– Bobs
Dec 28 '17 at 21:43