Device for determining network configurations of a neural network under a number of ancillary conditions

摘要

Device for the determination of a Pareto set of network configurations, identifying the network configurations for a neural network for a given application and determining the specified application in the form of training data provided, including a machine-readable storage medium, stored on the command which, when running through a computer, caused the computer to perform a procedure with the following steps:(a) provide (S1) a majority of randomly selected network configurations (a);b) training (S2) of neural networks configured with the network configurations (a) and depending on the corresponding determined hyperparameters (A) on the training data provided,where the training (S2) is carried out until a specified budget (b) is exhausted;(c) Determine (S3) a performance (accuracy) for each of the trained neural networks, in particular on part of the training data provided;(d) Evaluation (S4) of the trained neural networks (a) with respect to specified optimization objectives (n/pars)(e) Adding (S5) of a tube comprehensive network configurations (a), hyperparameters (A) and performance (accuracy) and optimization goals (n-pars) to a further training data set;(f) increase (S6), in particular double, the budget (b);(g) generate (S7) a new network configuration depending on the further training data set;(h) re-emptying from step (b) to (e) with the new network configurations and reducing the further training data set and then executing steps (f) and (g);where this repetition step is carried out until a maximum budget (bmax) is reached when the budget is increased; and(i) select the network configurations (a) from the next training data set, which corresponds to a Pareto set in terms of performance and at least one further optimization goal.