CORRECTNESS PRESERVING OPTIMIZATION OF DEEP NEURAL NETWORKS

• Main Authors: PERANANDAM PRAKASH MOHAN, SETHU RAMESH, RODIONOVA ALENA
• Format: Patent
• Language: Chinese; English
• Published: 30.06.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

A method for reducing the number of neurons in a trained deep neural network (DNN) includes classifying layer types in a plurality of hidden layers; evaluating the accuracy of the DNN using a validation set of data; and generating a layer specific ranking of neurons, wherein the generating includes: analyzing, using the validation set of data for one or more of the plurality of hidden layers, theactivation function for each neuron in the analyzed layers to determine an activation score for each neuron; and ranking, on a layer type basis, each neuron in the analyzed layers based on the neuron's activation score to generate a layer specific ranking of neurons. The method further includes removing a number of lower ranked neurons from the DNN that does not result in the DNN after the removalof selected lower ranked neurons to fall outside of an accuracy threshold limit. 本发明题为"深度神经网络的正确性保持优化"。本发明公开了一种用于减少受训深度神经网络(DNN)中的神经元数量的方法，该方法包括分类多个隐藏层中的层类型；使用数据验证集评估DNN的准确性；以及生成神经元的层特定排名，其中该生成包括：对多个隐藏层中的一个或多个层使用数据验证集，分析所分析的层