Data Object Classification Using an Optimized Neural Network

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

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.