US 12,596,931 B1 · Selection of inputs for training machine-trained network

Abstract

Some embodiments provide a method for training a machine-trained network that includes multiple parameters. The method propagates a batch of input training items through the network to generate output values and compute values of a loss function for each of the input training items. The method uses the computed values of the loss function for the input training items to adjust the parameters of the network. The method computes a gradient of the loss function for each of the input training items. The method selects input training items for subsequent batches of input training items based on a ratio of the value of the loss function to the gradient of the loss function for each of the input training items.

Claims20

Dependent claims

A method for training a machine-trained network comprising a plurality of parameters, the method comprising:

propagating a batch of input training items through the machine-trained network to generate output values and compute values of a loss function for each of the input training items;
using the computed values of the loss function for the input training items to adjust the parameters of the machine-trained network;
computing a gradient of the loss function for each of the input training items;
computing a ratio of the value of the loss function to the gradient of the loss function for each of the input training items;
selecting, using the computed ratios, input training items for subsequent batches of input training items;
and training the machine-trained network using the selected input training items.

3 more elements

Dependencies are inferred from the claim text.

Selection of inputs for training machine-trained network

Life of this patent

Selection of inputs for training machine-trained network

Life of this patent

Abstract

Claims20