US 2021/0232909 A1 · FREEZE-OUT AS A REGULARIZER IN TRAINING NEURAL NETWORKS

Abstract

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.

Claims22

Dependent claims

A system, comprising:

a memory that stores computer executable components;
and
a processor that executes computer executable components stored in the memory, wherein the computer executable components comprise:
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.

4 more elements

Dependencies are inferred from the claim text.

Freeze-out as a regularizer in training neural networks

Life of this patent

Freeze-out as a regularizer in training neural networks

Life of this patent

Abstract

Claims22