Abstract: Embodiments regard neural network (NN) obfuscation. A method can include receiving data representing the NN architecture. The NN architecture includes neurons, each neuron comprising corresponding neuron input weights, an activation function, and one or more interconnections between one or more other neurons of the neurons. The method can include mapping inputs to the neurons from a continuous domain to a discrete domain resulting in discretized neuron inputs. The method can include applying the activation function to the discretized neuron inputs resulting in discretized neuron outputs.

Abstract: Systems and methods are provided for updating data in a computer network. An exemplary method includes: receiving input data from at least one device; performing an extraction operation on the input data to extract at least one feature; producing at least one feature vector based on the at least one feature; performing a similarity analysis between the at least one feature vector and a plurality of other feature vectors from a plurality of autoencoders; selecting a first autoencoder from the plurality of autoencoders demonstrating significant similarity with at least one feature vector; determining whether the input data exhibits a recurring drift or a new drift; and training a new autoencoder using at least a portion of the input data.

Abstract: A method, comprising: receiving a first data set that is generated by satellite-based instrumentation; processing the first data set to detect an earth event and one or more characteristics of the earth event; and identifying a follow-up action based on the one or more characteristics and executing the follow-up action, wherein the event includes one or more of a weather event, an earth event, or a space event.

Abstract: Systems, devices, methods, and computer-readable media for evaluation and visualization of machine learning data drift. A method can include receiving a series of data indicating accuracy and confidence associated with classification of respective batches of input samples, and dynamically displaying, on the GUI, a concurrent plot of the accuracy and confidence as the series of data are received.

Abstract: Discussed herein are devices, systems, and methods for more flexible temporal graph network (TGN) graph interaction. A method includes executing first and second temporal graph networks (TGNs) to generate embeddings of respective first and second dynamic graphs, storing, as respective edge features of a first node of the first graph and a second node of the second graph, a memory state vector of the first node and a memory state vector of the second node, and determining, based on the embeddings and the edge features, a likelihood of an edge between nodes of the first graph.

Abstract: Subject matter regards improving machine learning techniques using informed pseudolabels. A method can include receiving previously assigned labels indicating an expected classification for data, the labels having a specified uncertainty, generating respective pseudolabels for the data based on the previously assigned labels, the data, a class vector determined by an ML model, and a noise model indicating, based on the specified uncertainty, a likelihood of the previously assigned label given the class, and substituting the pseudolabels for the previously assigned labels in a next epoch of training the ML model.

Abstract: Systems and methods for VIIRS image processing. The method can include receiving image data of immediately adjacent VIIRS image scans including a first image scan and a second image scan. The first image scan and the second image scan provide a partially overlapping view of a geographic area. The method can further involve resampling columns of pixels of the first image scan and the second image scan. The resampling can include selecting, in the first image scan and the second image scan, a subset of pixel values in each column that correspond to a specified geographic distance. The method can further involve upsampling the selected pixels to an equal number of pixels in each column resulting in upsampled pixel values and interpolating the upsampled pixel values to produce modified first and second image scans.

Abstract: Systems, devices, methods, and computer-readable media for evaluation and visualization of machine learning data drift. A method can include receiving a series of data indicating accuracy and confidence associated with classification of respective batches of input samples, and dynamically displaying, on the GUI, a concurrent plot of the accuracy and confidence as the series of data are received.

Abstract: A machine receives a large image having large image dimensions that exceed memory threshold dimensions. The large image includes metadata. The machine adjusts an orientation and a scaling of the large image based on the metadata. The machine divides the large image into a plurality of image tiles, each image tile having tile dimensions smaller than or equal to the memory threshold dimensions. The machine provides the plurality of image tiles to an artificial neural network. The machine identifies, using the artificial neural network, at least a portion of the target in at least one image tile. The machine identifies the target in the large image based on at least the portion of the target being identified in at least one image tile.

Abstract: Discussed herein are devices, systems, and methods for disentangling static and dynamic features of content. A method can include encoding by a transform disentangling autoencoder (AE), first content to generate first static features and first dynamic features and second content to generate second static features and second dynamic features, and constructing, by the AE, third content based on a combination of third static features and the first dynamic features and fourth content based on a combination of fourth static features and the second dynamic features, the third and fourth static features being determined based on the first static features and the second static features.

Abstract: Discussed herein are devices, systems, and methods for classification using a clustering autoencoder. A method can include obtaining content to be classified by the DNN classifier, and operating the DNN classifier to determine a classification of the received content, the DNN classifier including a clustering classification layer that clusters based on a latent feature vector representation of the content, the classification corresponding to one or more clusters that are closest to the latent feature vector providing the classification and a corresponding confidence.

Abstract: Discussed herein are devices, systems, and methods for classification using a clustering autoencoder. A method can include receiving, by an encoder of an autoencoder, content, the autoencoder trained using other content and corresponding labels, providing, by the encoder, a latent feature representation of the content to a decoder of the autoencoder, providing, by a clustering layer situated between the encoder and the decoder, a probability that the content belongs to a class of classes represented by respective clusters in a latent feature representation space based on a distance between the feature representation and the cluster, and providing, by the decoder, reconstructed content that is a construction of the content based on the latent feature representation.

Abstract: Systems, devices, methods, and computer-readable media for. A method can include receiving, from a laser scan device of a tolling station, a time series of distance measurements, determining, based on the time series of distance measurements, height measurements indicating a height of a vehicle from a surface of a road. generating, based on the height measurements, an image of the height measurements, and classifying, using the image as input to a convolutional neural network (CNN), the vehicle.

Abstract: Subject matter regards improving image segmentation or image annotation. A method can include receiving, through a user interface (UI), for each class label of class labels to be identified by the ML model and for a proper subset of pixels of the image data, data indicating respective pixels associated with the class label, partially training the ML model based on the received data, generating, using the partially trained ML model, pseudo-labels for each pixel of the image data for which a class label has not been received, and receiving, through the UT, a further class label that corrects a pseudo-label of the generated pseudo-labels.

Abstract: Discussed herein are devices, systems, and methods for disentangling static and dynamic features of content. A method can include encoding by a transform disentangling autoencoder (AE), first content to generate first static features and first dynamic features and second content to generate second static features and second dynamic features, and constructing, by the AE, third content based on a combination of third static features and the first dynamic features and fourth content based on a combination of fourth static features and the second dynamic features, the third and fourth static features being determined based on the first static features and the second static features.

Abstract: A neural network apparatus includes processing circuitry and memory. The memory stores a plurality of images of a target. The processing circuitry is configured to: access, from the memory, a first image and an identification of a centroid pixel of the target within the first image; generate, based on a geometry of the target and the centroid pixel, a confidence map indicating, for each pixel in the first image, a confidence value that the pixel includes the target; train, using the plurality of images of the target, including the first image and the confidence map, an artificial neural network to identify the target in visual data; and provide an output representing the trained artificial neural network.

Abstract: A computer architecture for an and-or neural network is disclosed. A computing machine accesses an input vector. The input vector comprises a numeric representation of an input to a neural network. The computing machine provides the input vector to the neural network comprising a plurality of ordered layers. The plurality of ordered layers are alternating AND-layers and OR-layers. Each of the plurality of ordered layers receives input from a preceding layer and/or provides output to a next layer. The computing machine generates an output of the neural network based on an output of a last one of the plurality of ordered layers in the neural network.

Abstract: A machine receives a large image having large image dimensions that exceed memory threshold dimensions. The large image includes metadata. The machine adjusts an orientation and a scaling of the large image based on the metadata. The machine divides the large image into a plurality of image tiles, each image tile having tile dimensions smaller than or equal to the memory threshold dimensions. The machine provides the plurality of image tiles to an artificial neural network. The machine identifies, using the artificial neural network, at least a portion of the target in at least one image tile. The machine identifies the target in the large image based on at least the portion of the target being identified in at least one image tile.

Abstract: A neural network apparatus includes processing circuitry and memory. The memory stores a plurality of images of a target. The processing circuitry is configured to: access, from the memory, a first image and an identification of a centroid pixel of the target within the first image; generate, based on a geometry of the target and the centroid pixel, a confidence map indicating, for each pixel in the first image, a confidence value that the pixel includes the target; train, using the plurality of images of the target, including the first image and the confidence map, an artificial neural network to identify the target in visual data; and provide an output representing the trained artificial neural network.

Abstract: Subject matter regards improving image segmentation or image annotation. A method can include receiving, through a user interface (UI), for each class label of class labels to be identified by the ML model and for a proper subset of pixels of the image data, data indicating respective pixels associated with the class label, partially training the ML model based on the received data, generating, using the partially trained ML model, pseudo-labels for each pixel of the image data for which a class label has not been received, and receiving, through the UT, a further class label that corrects a pseudo-label of the generated pseudo-labels.