Deep neural network multi-task hyper-parameter optimization method and device

Abstract

The invention discloses a deep neural network multitask hyper-parameter optimization method. The method comprises: firstly, a data training set of each task being subjected to model training to obtaina multi-task learning network model; secondly, predicting all points in an unknown region, screening candidate points from a prediction result, finally evaluating the screened candidate points, adding the candidate points and target function values of the candidate points into the data training set, and establishing a model, predicting, screening and evaluating again; and so on, until the maximumnumber of iterations is reached, finally selecting a candidate point corresponding to the maximum target function value from the data training set, that is, the hyper-parameter combination of each task in the multi-task learning network model. According to the method, the Gaussian model is replaced by the radial basis function neural network model, and the radial basis function neural network model is combined with multi-task learning and is applied to the Bayesian optimization algorithm to realize hyper-parameter optimization, so that the calculation amount of hyper-parameter optimization isgreatly reduced. The invention further discloses an electronic device and a storage medium.

Description

technical field [0001] The invention relates to hyperparameter optimization, in particular to a deep neural network multi-task hyperparameter optimization method, electronic equipment and a storage medium. Background technique [0002] For the optimization of hyperparameters, in most cases, manual tuning is used. For example, experienced professional scholars can set a better value for hyperparameters based on their years of experience, or continuously train the model and then adjust the value of hyperparameters based on experience. For beginners, you can only spend a lot of time tuning hyperparameters. Therefore, the automatic adjustment of hyperparameters has attracted the attention of many researchers. The earliest automatic parameter adjustment methods are grid search and random search methods. [0003] Grid search is a brute force search method. First, it is necessary to determine the range of multiple hyperparameters, and then combine multiple candidate solutions thr...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the deficiencies of the prior art, one of the purposes of the present invention is to provide a deep neural network multi-task hyperparameter optimization method, which can solve the problems of large amount of calculation for hyperparameter optimization in the prior art

[0007] The second object of the present invention

Images