Abstract: A method for training a generator. The generator is supplied with at least one actual signal that includes real or simulated physical measured data from at least one observation of the first area. The actual signal is translated by the generator into a transformed signal that represents the associated synthetic measured data in a second area. Using a cost function, an assessment is made concerning to what extent the transformed signal is consistent with one or multiple setpoint signals, at least one setpoint signal being formed from real or simulated measured data of the second physical observation modality for the situation represented by the actual signal. Trainable parameters that characterize the behavior of the generator are optimized with the objective of obtaining transformed signals that are better assessed by the cost function. A method for operating the generator, and that encompasses the complete process chain are also provided.

Abstract: Mechanisms are provided to implement a hardened ensemble artificial intelligence (AI) model generator. The hardened ensemble AI model generator co-trains at least two AI models. The hardened ensemble AI model generator modifies, based on a comparison of the at least two AI models, a loss surface of one or more of the at least two AI models to prevent an adversarial attack on one AI model, in the at least two AI models, transferring to another AI model in the at least two AI models, to thereby generate one or more modified AI models. At least one of the one or more modified AI models then processes an input to generate an output result.

Abstract: A set of classifiable data containing a plurality of classes is ingested. A target class within the plurality of classes is determined. Using the set of classifiable data, an interactive recall rate chart is generated, and the interactive recall rate chart shows a set of target class recall rates against a set of class recall rates for the remainder of the plurality of classes. The interactive recall rate chart is presented to a user. A target class recall rate selection from the set of target class recall rates is received from the user. The set of classifiable data is reclassified, based on the target class recall rate selection.

Abstract: Described herein are systems and methods for applying machine learning to telematics data to generate a unique driver fingerprint for an individual by periodically receiving telematics data generated at a plurality of sensors of a vehicle; standardizing the telematics data; aggregating the standardized telematics data; applying a trained machine learning model to embed the aggregated telematics data into a low-dimensional state; and generating a unique driver fingerprint for the individual, the driver fingerprint comprising a static component, a dynamic component, or both a static component and a dynamic component; including iterative repetition to update the dynamic component of the driver fingerprint.

Abstract: An electronic device including a deep memory model includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive input data to the deep memory model. The at least one processor is also configured to extract a history state of an external memory coupled to the deep memory model based on the input data. The at least one processor is further configured to update the history state of the external memory based on the input data. In addition, the at least one processor is configured to output a prediction based on the extracted history state of the external memory.

Abstract: This disclosure relates generally to artificial intelligence system, and more particularly to method and system for tracing a learning source of an explainable artificial intelligence (AI) model. In one example, the method may include receiving a desired behavior of the explainable AI model with respect to input data, generating a learning graph based on similarities among a plurality of learning sources with respect to the input data for the desired behavior and for a current behavior, retracing a learning of the explainable AI model by iteratively comparing the learning graph for the desired behavior and for the current behavior at each of a plurality of layers of the explainable AI model starting from an outer layer, and detecting the learning source responsible for the current behavior based on the retracing.

Abstract: A system for training a neural-network-based floating-point-to-binary feature vector encoder preserves the locality relationships between samples in an input space over to an output space. The system includes a neural network under training and a probability distribution loss function generator. The neural network has floating-point inputs and floating-point pseudo-bipolar outputs. The generator compares an input probability distribution constructed from floating-point cosine similarities of an input space and an output probability distribution constructed from floating-point pseudo-bipolar pseudo-Hamming similarities of an output space. The system includes a proxy vector set generator to take a random sampling of vectors from training data for a proxy set, a sample vector selector to select sample vectors from the training data and a KNN vector set generator to find a set of k nearest neighbors closest to each sample vector from said proxy set for a reference set.

Abstract: A method including monitoring, using a machine learning model, network events of a network. The machine learning model generates fraud scores representing a corresponding probability that a corresponding network event is fraudulent. The method also includes detecting a failure of the machine learning model to generate, within a threshold time, a given fraud score for a given network event. The method also includes determining, by the machine learning model and after the threshold time, the given fraud score. The method also includes logging, responsive to detecting the failure, the given network event in a first table, including logging the given fraud score. The method also includes determining a metric based on comparing the first table to a second table which logs at least the given fraud score and the fraud scores. The method also includes generating an adjusted machine learning model based on the metric.

Abstract: A system having multiple devices that can host different versions of an artificial neural network (ANN). In the system, changes to local versions of the ANN can be combined with a master version of the ANN. In the system, a first device can include memory that can store the master version, a second device can include memory that can store a local version of the ANN, and there can be many devices that store local versions of the ANN. The second device (or any other device of the system hosting a local version) can include a processor that can train the local version, and a transceiver that can transmit changes to the local version generated from the training. The first device can include a transceiver that can receive the changes to a local version, and a processing device that can combine the received changes with the master version.

Abstract: Provided is a computer-implemented method for implementing a hybrid deep neural network. The method may include generating a first model comprising a generalized matrix factorization model, the generalized matrix factorization model configured to determine one or more latent factors based on receiving transaction data associated with one or more payment transactions; generating a second model comprising a deep neural network model, the deep neural network model comprising a plurality of hidden layers; generating a combined model; and determining a rating for a payment account based on transaction data associated with a plurality of payment transactions, wherein the rating comprises an indication that the payment account will be used to conduct a plurality of payment transactions involving a merchant, and wherein the transaction data comprises merchant transaction data and user transaction data. A system and computer program product are also provided.

Abstract: Systems and methods for modifying a structure of an artificial neural network (ANN) are provided. An example method comprises receiving, by one or more processing units, a plurality of arrays of weights associated with the ANN, modifying, by the processing units, the plurality of arrays of weights to generate a further plurality of further arrays of weights, where after the modification the following conditions are satisfied: an amount of operations required for computing neurons of the ANN using the further plurality of further arrays of weights is less than an amount of operations required for computing same neurons of the ANN using the plurality of arrays of weights; and outputs of the neurons of the ANN computed using the plurality of arrays of weights are substantially equal to further outputs of the neurons of the ANN using the further plurality of further arrays of weights.

Abstract: A method for automatically generating an artificial neural network that encompasses modules and connections that link those modules, successive modules and/or connections being added to a current starting network. Modules and/or connections that are to be added are selected randomly from a predefinable plurality of possible modules and connections that can be added. A plurality of possible refinements of the current starting network respectively are generated by adding to the starting network modules and/or connections that are to be added. One of the refinements from the plurality of possible refinements is then selected in order to serve as a current starting network in a subsequent execution of the method.

Abstract: Systems are methods are provided for training an automated agent. The automated agent maintains a reinforcement learning neural network and generates, according to outputs of the reinforcement learning neural network, signals for communicating resource task requests. First and second task data are received. The task data are processed to compute a first performance metric reflective of performance of the automated agent relative to other entities in a first time interval, and a second performance metric reflective of performance of the automated agent relative to other entities in a second time interval. A reward for the reinforcement learning neural network that reflects a difference between the second performance metric and the first performance metric is computed and provided to the reinforcement learning neural network to train the automated agent.

Abstract: A control method based on an adaptive neural network model for dissolved oxygen of an aeration system includes: obtaining related water quality monitoring data of a sewage treatment plant, and performing data preprocessing on the related water quality monitoring data; performing principal component analysis on the preprocessed related water quality monitoring data and a dissolved oxygen concentration of the aeration system through a principal component analysis method, and determining a water quality parameter with a highest rate of contribution to a principal component; taking the water quality parameter with the highest rate of contribution to the principal component, and predicting a dissolved oxygen concentration of the aeration system; and optimizing a dissolved oxygen predictive value obtained by means of the adaptive neural network model to obtain an optimal regulation value, and performing online regulation on a fuzzy control system of the adaptive neural network model.

Abstract: Systems and methods for processing machine learning attributes are disclosed. An example method includes: identifying a user transaction associated with a set of transaction attributes and a first transaction status; selecting, based on a risk evaluation model, a first plurality of transaction attributes from the set of transaction attributes; modifying a first value of a first transaction attribute in the first plurality of transaction attributes to produce a first modified plurality of transaction attributes; determining, based on the risk evaluation model, that the first modified plurality of transaction attributes identify a second transaction status different from the first transaction status; and in response to the determining, identifying the first transaction attribute as a risk attribute associated with the user transaction.

Abstract: A system and a method of quantizing a pre-trained neural network, includes determining by a layer/channel bit-width determiner for each layer or channel of the pre-trained neural network a minimum quantization noise for the layer or the channel for each master bit-width value in a predetermined set of master bit-width values; and selecting by a bit-width selector for the layer or the channel the master bit-width value having the minimum quantization noise for the layer or the channel. In one embodiment, the minimum quantization noise for the layer or the channel is based on a square of a range of weights for the layer or the channel that is multiplied by a constant to a negative power of a current master bit-width value.

Abstract: Techniques for high-performance machine learning (ML) inference in heterogenous edge devices are described. A ML model trained using a variety of different frameworks is translated into a common format that is runnable by inferences engines of edge devices. The translated model is optimized in hardware-agnostic and/or hardware-specific ways to improve inference performance, and the optimized model is sent to the edge devices. The inference engine for any edge device can be accessed by a customer application using a same defined API, regardless of the hardware characteristics of the edge device or the original format of the ML model.

Abstract: Methods, systems, and computer program products are included for providing a predicted outcome to a user interface. An exemplary method includes receiving, from a user interface, a plurality of identifiers that identify objects. At the user interface, a target success function is selected corresponding to the plurality of identifiers. The target success function is mapped to at least one attribute of one or more attributes of the objects. The at least one attribute of the objects and one or more other attributes are queried. Data values are retrieved corresponding to the queried at least one attribute and the one or more other attributes. Based on the data values, an outcome of the target success function is predicted. The predicted outcome is provided to the user interface.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium. In one aspect, a method includes the actions of receiving a request to perform computations for a neural network on a hardware circuit having a matrix computation unit, the request specifying a transpose operation to be performed on a first neural network matrix; and generating instructions that when executed by the hardware circuit cause the hardware circuit to transpose the first neural network matrix by performing first operations, wherein the first operations include repeatedly performing the following second operations: for a current subdivision of the first neural network matrix that divides the first neural network matrix into one or more current submatrices, updating the first neural network matrix by swapping an upper right quadrant and a lower left quadrant of each current submatrix, and subdividing each current submatrix into respective new submatrices to update the current subdivision.

Abstract: A method of analysing and tracking machine systems has the steps of sensing operational data from equipment, the operational data comprising at least location, time, and one or more operational condition data related to the equipment; analysing the operational data to identify data patterns; logging the data patterns as events in a database; comparing the events to a database of predetermined patterns to classify each data pattern as a known event or an unknown event; updating the database to include a new data pattern related to any unknown events; and alerting a user to further classify the unknown events manually.