HYPER-PARAMETER SELECTION FOR DEEP CONVOLUTIONAL NETWORKS

摘要

Hyper-parameters are selected for training a deep convolutional network by selecting a number of network architectures as part of a database. Each of the network architectures includes one or more local logistic regression layer and is trained to generate a corresponding validation error that is stored in the database. A threshold error for identifying a good set of network architectures and a bad set of network architectures may be estimated based on validation errors in the database. The method also includes choosing a next potential hyper-parameter, corresponding to a next network architecture, based on a metric that is a function of the good set of network architectures. The method further includes selecting a network architecture, from among next network architectures, with a lowest validation error.

主权项

1. A method of selecting hyper-parameters for training a deep convolutional network, comprising:
selecting a number of network architectures as part of a database, each of the network architectures including at least one local logistic regression layer; training each of the network architectures to generate a corresponding validation error that is stored in the database; estimating a threshold error for identifying a good set of network architectures and a bad set of network architectures based at least in part on validation errors in the database; choosing a next potential hyper-parameter, corresponding to a next network architecture, based at least in part on a metric that is a function of the good set of network architectures; and selecting a network architecture, from among a plurality of next network architectures, with a lowest validation error.