is it possible to create an adaptative neural network that can change the number of its inputs and outputs without having to train it each time it changes? the neural netwrok has to take purchases and affect them to the delivery man that will minimize the global traveled distance.
Asked
Active
Viewed 112 times
0
-
Yes, it is. For example recurrent neural networks may process sequences with different lengths, that is, with a different number of inputs. – mikkola Jul 18 '22 at 12:17
-
you say the input data are purchases, you should specify more in details how these data look like to have a precise answer. mikkola might be right but maybe recurrent neural nets are not suitable for your use case. – Edoardo Guerriero Jul 18 '22 at 12:52
-
the customer can do purchase only two products( A and B) in specefic quantities. for exemple a customer can purchase only 1, 2, 3, 4, 5, 6, 7, 8, 11, 14 or 18 items of a product (A or B) or any linear combination of them. – achraf bennouali Jul 18 '22 at 13:07
-
the number of delivery men can vary from day to day but the quantities they can deliver per day is already fixed – achraf bennouali Jul 18 '22 at 13:12