Abstract: A network output is generated by feeding an input vector to an input layer of a neural network model having a plurality of neurons arranged in a sequence of layers, a plurality of neuron weights, and a plurality of neuron biases. The network output is used to determine an output relevance score. Relevance scores at a last layer of the sequence of layers are generated. Relevance scores are obtained at a first layer of the sequence of layers by reverse propagating the relevance scores generated at the last layer through the sequence of layers other than the last layer using the neuron weights and neuron biases. A feature relevance vector is formed based on the input vector and the relevance scores obtained at the first layer and included in a local explainability dataset, which is then used to generate a local explanation of a prediction of the neural network model.

Abstract: The layers of a neural network model are traversed in sequence one or more times while generating a plurality of relevance scores each time based on neuron weights and neuron biases of the neuron network model. Each relevance score of the plurality of relevance scores quantifies a relevance of a neuron in a lower layer of the sequence of layers to a higher layer of the sequence of layers. One or more relevance vectors can be populated from the plurality of relevance scores generated at the one or more times. Each of the relevance scores in each relevance vector quantifies a relevance of one of the input features to a task for which the neural network model is trained to perform. An explanation of a behavior of the neural network as a whole is generated based on the one or more relevance vectors.

Abstract: Methods, systems, and computer-readable storage media for providing a binary classifier include receiving a biased dataset, the biased data set including a plurality of records, each record being assigned to a class of a plurality of classes, one class including a majority class, performing data engineering on at least a portion of the biased dataset to provide a revised dataset, providing a trained deep autoencoder (DAE) by training a DAE using only records assigned to the majority class from the revised dataset, the trained DAE including a binary classifier that classifies records into one of the majority class and a minority class, validating the trained DAE using validation data that is based on at least a portion of the biased dataset, and providing the trained DAE for production use within a production system.

Abstract: Methods, systems, and computer-readable storage media for providing a binary classifier include receiving a biased dataset, the biased data set including a plurality of records, each record being assigned to a class of a plurality of classes, one class including a majority class, performing data engineering on at least a portion of the biased dataset to provide a revised dataset, providing a trained deep autoencoder (DAE) by training a DAE using only records assigned to the majority class from the revised dataset, the trained DAE including a binary classifier that classifies records into one of the majority class and a minority class, validating the trained DAE using validation data that is based on at least a portion of the biased dataset, and providing the trained DAE for production use within a production system.

Abstract: Combined color and depth data for a field of view is received. Thereafter, using at least one bounding polygon algorithm, at least one proposed bounding polygon is defined for the field of view. It can then be determined, using a binary classifier having at least one machine learning model trained using a plurality of images of known objects, whether each proposed bounding polygon encapsulates an object. The image data within each bounding polygon that is determined to encapsulate an object can then be provided to a first object classifier having at least one machine learning model trained using a plurality of images of known objects, to classify the object encapsulated within the respective bounding polygon.

Abstract: RGB-D data generated by at least one optical sensor for a field of view is received. Thereafter, the RGB-D data is bifurcated into (i) RGB data and (ii) depth data for the field of view. One or more bounding polygons are defined within the depth data that each characterize a window within the field of view encapsulating an object. The RGB data is then cropped using the bounding polygon(s). Image processing can later be applied to the cropped RGB data to identify at least one object therein. Related apparatus, systems, techniques and articles are also described.

Abstract: Image color data for a field of view is received. Thereafter, color segmentation can be performed on the image color data to define at least one bounding polygon that minimizes an amount of free space within each bounding polygon. The at least one bounding polygon is then used to crop the image color data to result in cropped image color data. Image processing can then be applied to the cropped image color data to identify at least one object therein. Related apparatus, systems, techniques and articles are also described.

Abstract: Combined color and depth data for a field of view is received. Thereafter, using at least one bounding polygon algorithm, at least one proposed bounding polygon is defined for the field of view. It can then be determined, using a binary classifier having at least one machine learning model trained using a plurality of images of known objects, whether each proposed bounding polygon encapsulates an object. The image data within each bounding polygon that is determined to encapsulate an object can then be provided to a first object classifier having at least one machine learning model trained using a plurality of images of known objects, to classify the object encapsulated within the respective bounding polygon.

Abstract: RGB-D data generated by at least one optical sensor for a field of view is received. Thereafter, the RGB-D data is bifurcated into (i) RGB data and (ii) depth data for the field of view. One or more bounding polygons are defined within the depth data that each characterize a window within the field of view encapsulating an object. The RGB data is then cropped using the bounding polygon(s). Image processing can later be applied to the cropped RGB data to identify at least one object therein. Related apparatus, systems, techniques and articles are also described.

Abstract: Image color data for a field of view is received. Thereafter, color segmentation can be performed on the image color data to define at least one bounding polygon that minimizes an amount of free space within each bounding polygon. The at least one bounding polygon is then used to crop the image color data to result in cropped image color data. Image processing can then be applied to the cropped image color data to identify at least one object therein. Related apparatus, systems, techniques and articles are also described.