US 12,271,821 B2
Training an autoencoder with a classifier
James K. Baker, Maitland, FL (US)
Assigned to D5AI LLC, Maitland, FL (US)
Filed by D5AI LLC, Maitland, FL (US)
Filed on Jul. 31, 2024, as Appl. No. 18/790,709.
Application 18/790,709 is a continuation of application No. 18/468,011, filed on Sep. 15, 2023, granted, now 12,061,986.
Application 18/468,011 is a continuation of application No. 18/147,313, filed on Dec. 28, 2022, granted, now 11,790,235, issued on Oct. 17, 2023.
Application 18/147,313 is a continuation of application No. 17/664,898, filed on May 25, 2022, granted, now 11,562,246, issued on Jan. 24, 2023.
Application 17/664,898 is a continuation of application No. 17/653,006, filed on Mar. 1, 2022, granted, now 11,392,832, issued on Jul. 19, 2022.
Application 17/653,006 is a continuation of application No. 16/618,910, granted, now 11,295,210, issued on Apr. 5, 2022, previously published as PCT/US2018/035275, filed on May 31, 2018.
Claims priority of provisional application 62/515,142, filed on Jun. 5, 2017.
Prior Publication US 2025/0053813 A1, Feb. 13, 2025
Int. Cl. G06N 3/082 (2023.01); G06N 3/044 (2023.01); G06N 3/084 (2023.01)
CPC G06N 3/082 (2013.01) [G06N 3/044 (2023.01); G06N 3/084 (2013.01)] 28 Claims
OG exemplary drawing
 
1. A method of training an autoencoder via machine learning, wherein the autoencoder comprises an encoder and a decoder, wherein each of the encoder and the decoder comprise a deep neural network, the method comprising:
processing, with a programmed computer system that comprises one or more processing units, each of multiple labeled training data examples in a labeled training dataset, wherein each of the multiple labeled training data examples in the labeled training dataset has a corresponding label, and wherein the processing comprises:
in a forward propagation phase:
generating, by the encoder, an encoder output;
generating, by the decoder, an output from the encoder output for the labeled training data example, wherein the decoder is trained, for each labeled training data example, to generate the labeled training data example from the encoder output and wherein the decoder has a first objective function; and
generating, by a classifier, a classification output from the encoder output for the labeled training data example, wherein the classifier is trained, for each labeled training data example, to generate a corresponding label for the labeled training data example, wherein the classifier has a second objective function, and wherein the classifier comprises a deep neural network; and
after the forward propagation phase, in a back propagation phase:
generating, by the decoder, a first set of partial derivatives of a first cost function for the first objective through the decoder;
generating, by the classifier, a second set of partial derivatives of a second cost function for the second objective through the classifier; and
generating, by the encoder, a third set of partial derivatives of a third cost function with respect to both the first and second objectives through the encoder; and
updating, by the computer system, learned parameters for the encoder based on the third set of partial derivatives.