Neural Network Inference when only 1 input changes

Edward Hamilton asked 5 months ago

I’m interested in using a neural network in the objective function of local search based combinatorial optimization (e.g. scheduling). During optimization, often only 1 (or a few) decision variables (inputs to NN) change and we want to know the resultant objective function. So my question is, are there NN inference engines that have memory and if only 1 input changes would incrementally infer the output?

1 Answers
Best Answer
Chris Staff answered 1 month ago

Isn’t this an example of multiclass classification? Given a combination of input features, choose the most appropriate objective function.

Your Answer

19 + 2 =