Data Object Classification Using an Optimized Neural Network

Number: 20210150316
Published: 2021-05-20
Filed: 2020-03-03
Assignee: Disney Enterprises, Inc.
Inventors: Riemenschneider; Hayko Jochen Wilhelm, Helminger; Leonhard Markus, Schroers; Christopher Richard, Djelouah; Abdelaziz
CPC: G06N3/045; G06F18/24; G06V10/7753; G06V10/75; G06N3/08; G06N3/09; G06V10/82; G06N3/0499; G06F18/2155; G06N3/048; G06V10/764; G06V10/776
Verdict: Set aside generic ML data classification, business
Source: Google Patents · FreePatentsOnline

Abstract

A system includes a computing platform having a hardware processor and a memory storing a software code and a neural network (NN) having multiple layers including a last activation layer and a loss layer. The hardware processor executes the software code to identify different combinations of layers for testing the NN, each combination including candidate function(s) for the last activation layer and candidate function(s) for the loss layer. For each different combination, the software code configures the NN based on the combination, inputs, into the configured NN, a training dataset including multiple data objects, receives, from the configured NN, a classification of the data objects, and generates a performance assessment for the combination based on the classification. The software code determines a preferred combination of layers for the NN including selected candidate functions for the last activation layer and the loss layer, based on a comparison of the performance assessments.

Background

BACKGROUND

Datasets are a subset of real-world distributions and contain biases and noise. Despite being carefully constructed, deep neural networks (NNs) trained as classifiers on noisy datasets tend to inherit their biases and errors. Those biases and errors present as noise in a dataset may take the form of incorrect labels applied to the data, missing labels, superfluous labels, as well as label frequency imbalance, for instance. Moreover, extreme noise is a typical characteristic of unstructured datasets including highly varied data for which it is often not feasible to utilize standard data preparation techniques, such as structuring or cleansing for example, before deep learning takes place.

A recent conventional solution to the problem of noisy datasets assigns a specific focus for each label and sample in the dataset. However, calculation of the focal loss requires additional weights and tuning, which limits the usefulness of the solution in applications for which it is not specifically designed. Another conventional approach relies on a pure softmax activation and multi-class cost calculation, but is typically not robust enough for unstructured data. SUMMARY

There are provided systems and methods for performing data object classification using an optimized neural network, substantially as shown in and/or described in connection with at least one of the figures, and as set forth more completely in the claims.

Claims

1. A system for classifying data objects, the system comprising: a computing platform including a hardware processor and a system memory; a software code and a neural network (NN) stored in the system memory, the NN having a plurality of layers including one or more activation layers and a loss layer, the one or more activation layers comprising a last activation layer; the hardware processor configured to execute the software code to: identify a plurality of different combinations of layers for testing the NN, each combination of the plurality of different combinations of layers including one or more candidate functions for the last activation layer and one or more candidate functions for the loss layer; for each combination of the plurality of different combinations of layers: configure the NN based on the each combination; input, into the configured NN, a training dataset including a plurality of data objects; receive, from the configured NN, a classification of the plurality of data objects in the training dataset; generate a performance assessment for the each combination based on the classification; and determine a preferred combination of layers for the NN from among the plurality of different combinations of layers based on a comparison of the performance assessments, the preferred combination of layers comprising a selected candidate amongst the one or more candidate functions for the last activation layer and a selected candidate amongst the one or more candidate functions for the loss layer. || 10. A method for use by a system for classifying data objects, the system including a computing platform having a hardware processor and a system memory storing a software code and a neural network (NN), the NN having a plurality of layers including one or more activation layers and a loss layer, the or more activation layers comprising a last activation layer, the method comprising: identifying, by the software code executed by the hardware processor, a plurality of different combinations of layers for testing the NN, each combination of the plurality of different combinations of layers including one or more candidate functions for the last activation layer and one or more candidate functions for the loss layer; for each combination of the plurality of different combinations of layers: configuring, by the software code executed by the hardware processor, the NN based on the each combination; inputting into the configured NN, by the software code executed by the hardware processor, a training dataset including a plurality of data objects; receiving from the configured NN, by the software code executed by the hardware processor, a classification of the plurality of data objects in the training dataset; generating, by the software code executed by the hardware processor, a performance assessment for the each combination based on the classification; and determining, by the software code executed by the hardware processor, a preferred combination of layers for the NN from among the plurality of different combinations of layers based on a comparison of the performance assessments, the preferred combination of layers comprising a selected candidate amongst the one or more candidate functions for the last activation layer and a selected candidate amongst the one or more candidate functions for the loss layer. || 19. A method for use by a system having a hardware processor and a system memory storing a software code and a neural network (NN), to generate a training dataset for training the NN to classify images, the method comprising: obtaining, by the software code executed by the hardware processor, a plurality of real images; compositing, by the software code executed by the hardware processor, the plurality of real images to form a montage of the plurality of real images; identifying, by the software code executed by the hardware processor, a plurality of labels for association with the montage; and labeling, by the software code executed by the hardware processor, the montage using one or more of the plurality of identified labels to generate the training dataset; wherein noise is parametrically introduced into the training dataset, resulting in a subset of the training dataset being purposely mislabeled.