Abstract: A method for training an automated learning system includes processing training input with a first neural network and processing the output of the first neural network with a second neural network. The input layer of the second neural network corresponding to the output layer of the first neural network. The output layer of the second neural network corresponding to the input layer of the first neural network. An objective function is determined using the output of the second neural network and a predetermined modification magnitude. The objective function is approximated using random Cauchy projections which are propagated through the second neural network.

Abstract: A machine learning system includes encoder and decoder networks. The machine learning system is configured to obtain input data, which includes sensor data and a radius of an p norm ball of admissible perturbations. Input bounding data is generated based on the input data. First bounding data and second bounding data are generated by respectively propagating the input bounding data on first and second outputs of the encoder network. Third bounding data is generated in association with a latent variable based on the first bounding data and the second bounding data. Fourth bounding data is generated by propagating the third bounding data on an output of the decoder network. A robustness certificate is established with respect to the input data by generating a lower bound of an evidence lower bound based on the first, second, third, and fourth bounding data.

Abstract: Regularized training of a Deep Equilibrium Model (DEQ) is provided. A regularization term is computed using a predefined quantity of random samples and the Jacobian matrix of the DEQ, the regularization term penalizing the spectral radius of the Jacobian matrix. The regularization term is included in an original loss function of the DEQ to form a regularized loss function. A gradient of the regularized loss function is computed with respect to model parameters of the DEQ. The gradient is used to update the model parameters.

Abstract: An energy meter is configured to determine component waveforms that form a measured waveform. The meter inputs the waveform into one or more entries of a data structure, each entry of the one or more entries of the data structure storing a weight value that is determined based at least in part on values of the data signatures representing the plurality of remote devices, each entry being connected to one or more other entries of the data structure. The meter, for each of the one or more entries, generates an output value by performing an arithmetic operation on the waveform stored at that entry, the arithmetic operation comprising a function of the weight value. The meter identifies, from among the data signatures, one or more particular data signatures that are represented in the waveform. The meter determines, based on the particular data signatures, an operational state of another device.

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 to a 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: In a method for training a first neural network a superposed classification is back-propagated through a second neural network. An output value of the second neural network is utilized to determine whether the input of the first neural network is adversarial.

Abstract: Various embodiments of the present disclosure can include systems, methods, and non-transitory computer readable media configured to train a Bayesian network model based on a given set of data. Information associated with a user can be received. The information can include aggregated energy consumption data at one or more low frequency time intervals. At least a portion of the information can be inputted into the Bayesian network model. A plurality of energy consumption values for a plurality of energy consumption sources associated with the user can be inferred based on inputting the at least the portion of the information into the Bayesian network model.

Abstract: Various embodiments of the present disclosure can include systems, methods, and non-transitory computer readable media configured to train a Bayesian network model based on a given set of data. Information associated with a user can be received. The information can include aggregated energy consumption data at one or more low frequency time intervals. At least a portion of the information can be inputted into the Bayesian network model. A plurality of energy consumption values for a plurality of energy consumption sources associated with the user can be inferred based on inputting the at least the portion of the information into the Bayesian network model.

Abstract: A machine learning system includes encoder and decoder networks. The machine learning system is configured to obtain input data, which includes sensor data and a radius of an p norm ball of admissible perturbations. Input bounding data is generated based on the input data. First bounding data and second bounding data are generated by respectively propagating the input bounding data on first and second outputs of the encoder network. Third bounding data is generated in association with a latent variable based on the first bounding data and the second bounding data. Fourth bounding data is generated by propagating the third bounding data on an output of the decoder network. A robustness certificate is established with respect to the input data by generating a lower bound of an evidence lower bound based on the first, second, third, and fourth bounding data.

Abstract: Various embodiments of the present disclosure can include systems, methods, and non-transitory computer readable media configured to identify a set of features associated with at least one of a collection of residences or an energy billing period. Measured energy consumption information and a plurality of feature values can be acquired for each residence in the collection of residences. Each feature value in the plurality of feature values can correspond to a respective feature in the set of features. A regression model can be trained based on the measured energy consumption information and the plurality of features values for each residence in the collection of residences. At least one expected consumption value and at least one efficient consumption value can be determined based on the regression model.

Abstract: A method for training an automated learning system includes processing training input with a first neural network and processing the output of the first neural network with a second neural network. The input layer of the second neural network corresponding to the output layer of the first neural network. The output layer of the second neural network corresponding to the input layer of the first neural network. An objective function is determined using the output of the second neural network and a predetermined modification magnitude. The objective function is approximated using random Cauchy projections which are propagated through the second neural network.

Abstract: In a method for training a first neural network a superposed classification is back-propagated through a second neural network. An output value of the second neural network is utilized to determine whether the input of the first neural network is adversarial.

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 to a 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: Various embodiments of the present disclosure can include systems, methods, and non-transitory computer readable media configured to identify a set of features associated with at least one of a collection of residences or an energy billing period. Measured energy consumption information and a plurality of feature values can be acquired for each residence in the collection of residences. Each feature value in the plurality of feature values can correspond to a respective feature in the set of features. A regression model can be trained based on the measured energy consumption information and the plurality of features values for each residence in the collection of residences. At least one expected consumption value and at least one efficient consumption value can be determined based on the regression model.

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 to a 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: 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: An energy meter is configured to determine component waveforms that form a measured waveform. The meter inputs the waveform into one or more entries of a data structure, each entry of the one or more entries of the data structure storing a weight value that is determined based at least in part on values of the data signatures representing the plurality of remote devices, each entry being connected to one or more other entries of the data structure. The meter, for each of the one or more entries, generates an output value by performing an arithmetic operation on the waveform stored at that entry, the arithmetic operation comprising a function of the weight value. The meter identifies, from among the data signatures, one or more particular data signatures that are represented in the waveform. The meter determines, based on the particular data signatures, an operational state of another device.

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 to a 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: 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 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 to 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.