首页>
外国专利>
MICROTRAINING FOR ITERATIVE FEW-SHOT REFINEMENT OF A NEURAL NETWORK
MICROTRAINING FOR ITERATIVE FEW-SHOT REFINEMENT OF A NEURAL NETWORK
展开▼
机译:神经网络迭代近摄细化的微调
展开▼
页面导航
摘要
著录项
相似文献
摘要
The disclosed microtraining techniques improve accuracy of trained neural networks by performing iterative refinement at low learning rates using a relatively short series microtraining steps. A neural network training framework receives the trained neural network along with a second training dataset and set of hyperparameters. The neural network training framework produces a microtrained neural network by adjusting one or more weights of the trained neural network using a lower learning rate to facilitate incremental accuracy improvements without substantially altering the computational structure of the trained neural network. The microtrained neural network may be assessed for changes in accuracy and/or quality. Additional microtraining sessions may be performed on the microtrained neural network to further improve accuracy or quality.
展开▼