FREEZE-OUT AS A REGULARIZER IN TRAINING NEURAL NETWORKS

• Main Authors: AVINASH GOPAL BILIGERI, FERENCZI LEHEL, TAN TAO, TOROK LEVENTE IMRE, CHO SATOSHI, TEGZES PAL
• Format: Patent
• Language: Chinese; English
• Published: 27.07.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

Freeze-out as a regularizer in training neural networks. Systems and techniques that facilitate freeze-out as a regularizer in training neural networks are presented. A system can include a memory and a processor that executes computer executable components. The computer executable components can include: an assessment component that identifies units of a neural network, a selection component that selects a subset of units of the neural network, and a freeze-out component that freezes the selected subset of units of the neural network so that weights of output connections from the frozen subset of units will not be updated for a training run. 本发明题为在训练神经网络中作为正则化器的冻结。本发明提出了促进在训练神经网络中作为正则化器的冻结的系统和技术。系统可包括存储器和执行计算机可执行组件的处理器。该计算机可执行组件可包括：评估组件，该评估组件识别神经网络的单元；选择组件，该选择组件选择神经网络的单元的子集；和冻结组件，该冻结组件冻结神经网络的单元的选定子集，使得针对训练运行将不更新来自单元的冻结子集的输出连接的权重。