Device and method for training a classifier using an invertible factorization model

A classifier configured to determine an output signal characterizing a classification of an input signal, the classifier being trained by:

• determining a first training input signal;
• determining a first latent representation including a plurality of factors based on the first training input signal using an invertible factorization model,
• wherein the invertible factorization model includes:
• a plurality of functions, wherein any one function from the plurality of functions is continuous and almost everywhere continuously differentiable, wherein the function is further configured to accept either the training input signal or at least one of the factors provided by another function of the plurality of functions as an input and wherein the function is further configured to provide at least one of the factors, wherein the at least one of the factors is either provided as at least part of the latent representation or is provided as at least part of an input of another function of the plurality of functions, wherein there exists an inverse function that corresponds with the function, is continuous, is almost everywhere continuously differentiable and is configured to determine an input of a layer based on the at least one factor provided from the function;
• determining a second latent representation by adapting at least one of the factors of the first latent representation;
• determining a second training input signal based on the second latent representation using the invertible factorization model;
• and
• training the classifier based on the second training input signal.

A training system configured to train a classifier, wherein the classifier is configured to determine an output signal characterizing a classification of an input signal, the training system configured to:

• determine a first training input signal;
• determine a first latent representation including a plurality of factors based on the first training input signal using an invertible factorization model,
• wherein the invertible factorization model includes:
• a plurality of functions, wherein any one function from the plurality of functions is continuous and almost everywhere continuously differentiable, wherein the function is further configured to accept either the training input signal or at least one of the factors provided by another function of the plurality of functions as an input and wherein the function is further configured to provide at least one of the factors, wherein the at least one of the factors is either provided as at least part of the latent representation or is provided as at least part of an input of another function of the plurality of functions, wherein there exists an inverse function that corresponds with the function, is continuous, is almost everywhere continuously differentiable and is configured to determine an input of a layer based on the at least one factor provided from the function;
• determine a second latent representation by adapting at least one of the factors of the first latent representation;
• determine a second training input signal based on the second latent representation using the invertible factorization model;
• and
• train the classifier based on the second training input signal.

A non-transitory machine-readable storage medium which is stored a computer program for training a classifier, wherein the classifier is configured to determine an output signal characterizing a classification of an input signal, the computer program, when executed by a processor, causing the processor to perform the following steps:

• determining a first training input signal;
• determining a first latent representation including a plurality of factors based on the first training input signal using an invertible factorization model,
• wherein the invertible factorization model includes:
• a plurality of functions, wherein any one function from the plurality of functions is continuous and almost everywhere continuously differentiable, wherein the function is further configured to accept either the training input signal or at least one of the factors provided by another function of the plurality of functions as an input and wherein the function is further configured to provide at least one of the factors, wherein the at least one of the factors is either provided as at least part of the latent representation or is provided as at least part of an input of another function of the plurality of functions, wherein there exists an inverse function that corresponds with the function, is continuous, is almost everywhere continuously differentiable and is configured to determine an input of a layer based on the at least one factor provided from the function;
• determining a second latent representation by adapting at least one of the factors of the first latent representation;
• determining a second training input signal based on the second latent representation using the invertible factorization model;
• and
• training the classifier based on the second training input signal.