Abstract: A computational method for training a classifier. The method includes receiving a training data set comprised of pairs of training input and output signals, the classifier parameterized by parameters, a class-dependent allowed perturbation for each of at least two different classes and including a first class-dependent allowed perturbation for a first class and a second class-dependent allowed perturbation for a second class, and a loss function. The method further includes partitioning the training data set into a first subset labelled with a first label and a second subset labelled with a second label. The method also includes calculating a first loss in response to the first subset and the first class-dependent allowed perturbation and a second loss calculated in response to the second subset and the second class-dependent allowed perturbation. The method also includes updating the parameters in response to the first and second losses to obtain updated parameters.

Abstract: A method for training a machine-learning network includes receiving an input data from a sensor. The input data includes a perturbation. The method also includes obtaining a worst-case bound on a classification error and loss for perturbed versions of the input data. The method also includes training a classifier, where the classifier includes a plurality of classes, including a plurality of additional abstain classes. Each additional abstain class of the plurality of additional abstain classes is determined in response to at least bounding the input data. The method also includes outputting a classification in response to the input data indicating one of the plurality of classes and outputting a trained classifier in response to exceeding a convergence threshold. The trained classifier is configured to detect at least one additional abstain class of the plurality of additional abstain classes in response to obtaining the worst-case bound.

Abstract: A computer-program product storing instructions which, when executed by a computer, cause the computer to, for one or more iterations, update parameters associated with a machine-learning network utilizing perturbations for input data, wherein the perturbations are sampled utilizing Markov chain Monte Carlo, identify a loss value associated with each perturbation in each iteration, and evaluate the machine learning network by identifying an average loss value across each iteration and outputting the average loss value.

Abstract: A method for estimating input certainty for a neural network using generative modeling. The method includes generating, using an input data, two or more input data and embedding vector combinations and providing, at the neural network, each of the two or more input data and embedding vector combinations. The method also includes receiving, from the neural network, an output value for each input data and embedding vector combination of the two or more input data and embedding vector combinations. The method also includes computing a variance value for the output values of each respective input data and embedding vector combinations and determining a certainty value for the input data based on the variance value.

Abstract: Systems and methods for operating a deep equilibrium (DEQ) model in a neural network are disclosed. DEQs solve for a fixed point of a single nonlinear layer, which enables decoupling the internal structure of the layer from how the fixed point is actually computed. This disclosure discloses that such decoupling can be exploited while substantially enhancing this fixed point computation using a custom neural solver.

Abstract: A convolutional neural network system includes a sensor and a controller, wherein the controller is configured to receive an image from the sensor, divide the image into patches, each patch of size p, extract, via a first convolutional layer, a feature map having a number of channels based on a feature detector of size p, wherein the feature detector has a stride equal to size p, refine the feature map by alternatingly applying depth-wise convolutional layers and point-wise convolutional layers to obtain a refined feature map, wherein the number of channels in the feature map and the size of the feature map remains constant throughout all operations in the refinement; and output the refined feature map.

Abstract: Methods and systems for inferring data to supplement an input utilizing a neural network, and training such a system, are disclosed. In embodiments, an input is received from a sensor at the neural network. Iterations of approximate probabilities can be determined based on hidden-to-hidden Markov random field (MRF) potentials, observed-to-hidden MRF potentials, and unary MRF potentials. A constant can be identified using a root-finding algorithm. The iterations can continue until convergence. The final iteration of the approximate probability can be used to supplement the input to produce an output.

Abstract: A computer-implemented method for a classification and training a neural network includes receiving input at the neural network, wherein the input includes a plurality of resolution inputs of varying resolutions, outputting a plurality of feature tensors for each corresponding resolution of the plurality of resolution inputs, fusing the plurality of feature tensors utilizing upsampling or down sampling for the vary resolutions, utilizing an equilibrium solver to identify one or more prediction vectors from the plurality of feature tensors, and outputting a loss in response to the one or more prediction vectors.

Abstract: A system for controlling a physical system via segmentation of an image includes a controller. The controller may be configured to receive an image of n pixels from a first sensor, and an annotation of the image from a second sensor, form a coupling matrix, k class vectors each of length n, and a bias coefficient based on the image and the annotation, generate n pixel vectors each of length n based on the coupling matrix, class vectors, and bias coefficient create a single segmentation vector of length n from the pixel vectors wherein each entry in the segmentation vector identifies one of the k class vectors, output the single segmentation vector; and operate the physical system based on the single segmentation vector.

Abstract: Various embodiments of the present disclosure can include systems, methods, and non-transitory computer readable media configured to select a set of signals relating toa plurality of energy usage conditions. Signal values for the set of signals can be determined. Machine learning can be applied to the signal values to identify energy usage conditions associated with non-technical loss.

Abstract: A computer-implemented method for training a machine-learning network. The method includes receiving an input data from a sensor, wherein the input data is indicative of image, radar, sonar, or sound information, generating an input data set utilizing the input data, wherein the input data set includes perturbed data, sending the input data set to a robustifier, wherein the robustifier is configured to clean the input data set by removing perturbations associated with the input data set to create a modified input data set, sending the modified input data set to a pretrained machine learning task, training the robustifier to obtain a trained robustifier utilizing the modified input data set, and in response to convergence of the trained robustifier to a first threshold, output the trained robustifier.

Abstract: A multimodal perception system for an autonomous vehicle includes a first sensor that is one of a video, RADAR, LIDAR, or ultrasound sensor, and a controller. The controller may be configured to, receive a first signal from a first sensor, a second signal from a second sensor, and a third signal from a third sensor, extract a first feature vector from the first signal, extract a second feature vector from the second signal, extract a third feature vector from the third signal, determine an odd-one-out vector from the first, second, and third feature vectors via an odd-one-out network of a machine learning network, based on inconsistent modality prediction, fuse the first, second, and third feature vectors and odd-one-out vector into a fused feature vector, output the fused feature vector, and control the autonomous vehicle based on the fused feature vector.

Abstract: The disclosed technology can acquire a first set of data from a first group of data sources including a plurality of network components within an energy delivery network. A first metric indicating a likelihood that a particular network component, from the plurality of network components, is affected by cyber vulnerabilities can be generated based on the first set of data. A second set of data can be acquired from a second group of data sources including a collection of services associated with the energy delivery network. A second metric indicating a calculated impact on at least a portion of the energy delivery network when the cyber vulnerabilities affect the particular network component can be generated based on the second set of data. A third metric indicating an overall level of cybersecurity risk associated with the particular network component can be generated based on the first metric and the second metric.

Abstract: A system for training a neural work that includes an input interface for accessing input data for the neural network and a processor in communication with the input interface. The processor is programmed to receive input at the neural network and output a trained neural networking utilizing a forward prorogation and a backward propagation, wherein the forward propagation includes utilizing a root-finding procedure to identify a fixed point associated with one or more parameters of the neural network, wherein the backward propagation includes identifying a derivative of a loss associated with the parameters of the network.

Abstract: A computer-implemented method includes receiving a coarse mesh input that includes a first set of nodes, wherein the coarse mesh is input to a computational fluid dynamics solver with physical parameters to obtain a coarse mesh solution, receiving a fine mesh input that is of a second set of nodes, wherein the second set of nodes includes more nodes than the first set of nodes, concatenating the fine mesh input with the physical parameters and run the concatenation through a graph convolution layer to obtain a fine mesh hidden layer, upsampling the coarse mesh solution to obtain a coarse mesh upsample including a same number of nodes as the second set of nodes, and outputting a prediction in response to at least the coarse mesh upsample.

Abstract: The present disclosure provides systems and methods that may advantageously apply machine learning to detect and ascribe network interruptions to specific components or nodes within the network. In an aspect, the present disclosure provides a computer-implemented method comprising: mapping a network comprising a plurality of islands that are capable of dynamically changing by splitting and/or merging of one or more islands, wherein the plurality of islands comprises a plurality of individual components; and detecting and localizing one or more local events at an individual component level as well as at an island level using a disaggregation model.

Abstract: A linguistic system includes a controller. The controller may be configured to receive a query and document, tokenize the query into a sequence of query tokens and tokenize the document into a sequence of document tokens, generate a matrix of token pairs for each of the query and the document tokens, retrieve for each entry in the matrix of token pairs, a precomputed similarity score produced by a neural conditional translation probability network, wherein the neural network has been trained in a ranking task using a corpus of paired queries and respective relevant documents, produce a ranking score for each document with respect to each query via a product-of-sum aggregation of each of the similarity scores for the respective query; and output the document and associated ranking score of the document.

Abstract: The disclosed technology can acquire a first set of data from a first group of data sources including a plurality of network components within an energy delivery network. A first metric indicating a likelihood that a particular network component, from the plurality of network components, is affected by cyber vulnerabilities can be generated based on the first set of data. A second set of data can be acquired from a second group of data sources including a collection of services associated with the energy delivery network. A second metric indicating a calculated impact on at least a portion of the energy delivery network when the cyber vulnerabilities affect the particular network component can be generated based on the second set of data. A third metric indicating an overall level of cybersecurity risk associated with the particular network component can be generated based on the first metric and the second metric.

Abstract: The present disclosure provides systems and methods that may advantageously apply machine learning to detect and ascribe network interruptions to specific components or nodes within the network. In an aspect, the present disclosure provides a computer-implemented method comprising: mapping a network comprising a plurality of islands that are capable of dynamically changing by splitting and/or merging of one or more islands, wherein the plurality of islands comprises a plurality of individual components; and detecting and localizing one or more local events at an individual component level as well as at an island level using a disaggregation model.

Abstract: A computer-implemented method for training a machine-learning network, wherein the network includes receiving an input data from a sensor, wherein the input data includes data indicative of an image, wherein the sensor includes a video, radar, LiDAR, sound, sonar, ultrasonic, motion, or thermal imaging sensor, generating an adversarial version of the input data utilizing an optimizer, wherein the adversarial version of the input data utilizes a subset of the input data, parameters associated with the optimizer, and one or more perturbation tiles, determining loss function value in response to the adversarial version of the input data and a classification of the adversarial version of the input data, determining a perturbation tile in response the loss function value associated with one or more subsets of the adversarial version of the input data, and output a perturbation that includes at least the perturbation tile.