Abstract: Embodiments of the present disclosure include systems and methods for reducing hardware resource utilization by residual neural networks. In some embodiments, a first matrix is received at a layer included in a neural network. The first matrix is compressed to produce a second matrix. The second matrix has a reduced dimensionality relative to a dimensionality of the first matrix. The second matrix is processed through a network block in the layer included in the neural network. The processed second matrix is expanded to produce a third matrix. The third matrix has a dimensionality that is equal to a dimensionality of the first matrix. The third matrix is added to the first matrix to produce a fourth matrix.

Abstract: The invention proposes a method of training a convolutional neural network in which, at each convolution layer, weights for one seed convolutional filter per layer are updated during each training iteration. All other convolutional filters are polynomial transformations of the seed filter, or, alternatively, all response maps are polynomial transformations of the response map generated by the seed filter.

Abstract: A system and method of detecting an aberrant message is provided. An ordered set of words within the message is detected. The set of words found within the message is linked to a corresponding set of expected words, the set of expected words having semantic attributes. A set of grammatical structures represented in the message is detected, based on the ordered set of words and the semantic attributes of the corresponding set of expected words. A cognitive noise vector comprising a quantitative measure of a deviation between grammatical structures represented in the message and an expected measure of grammatical structures for a message of the type is then determined. The cognitive noise vector may be processed by higher levels of the neural network and/or an external processor.

Abstract: A machine learning environment utilizing training data generated by customer environments. A reinforced learning machine learning environment receives and processes training data generated by independently hosted, or decoupled, customer environments. The reinforced learning machine learning environment corresponds to machine learning clusters that receive and process training data sets provided by the decoupled customer environments. The customer environments include an agent process that collects training data and forwards the training data to the machine learning clusters without exposing the customer environment. The machine learning clusters can be configured in a manner to automatically process the training data without requiring additional user inputs or controls to configured the application of the reinforced learning machine learning processes.

Abstract: The invention specifies a method of improving a subsequent iterations of a generative network by adding a ranking loss to the total loss for the network, the ranking loss representing the marginalized difference between a discriminator score for a generated image in one iteration of the generative network and the discriminator score for a real image from a subsequent iteration of the generative network.

Abstract: Techniques for tackling delayed user response by modifying training data for machine-learned models are provided. In one technique, a first machine-learned model generates a score based on a set of feature values. A training instance is generated based on the set of feature values. An attribute of the training instance is modified based on the score to generate a modified training instance. The attribute may be an importance weight of the training instance or a label of the training instance. The modified training instance is added to a training data. One or more machine learning techniques are used to train a second machine-learned model based on the training data.

Abstract: Systems, methods, and apparatuses for providing dynamic, prioritized spectrum utilization management. The system includes at least one monitoring sensor, at least one data analysis engine, at least one application, a semantic engine, a programmable rules and policy editor, a tip and cue server, and/or a control panel. The tip and cue server is operable utilize the environmental awareness from the data processed by the at least one data analysis engine in combination with additional information to create actionable data.

Abstract: A combination of machine learning models is provided, according to certain aspects, by a data-aggregation circuit, and a computer server. The data-aggregation circuit is used to assimilate respective sets of output data from at least one of a plurality of circuits to create a new data set, the respective sets of output data being related in that each set of output data is in response to a common data set processed by the machine learning circuitry in the at least one of the plurality of circuits. The computer server uses the new data set to train machine learning operations in at least one of the plurality of circuits.

Abstract: A system for using hash keys to preserve privacy across multiple tasks is disclosed. The system may provide training batch(es) of input observations each having a customer request and stored task to an encoder, and assign a hash key(s) to each of the stored tasks. The system may provide a new batch of input observations with a new customer request and new task to the encoder. The encoder may generate a new hash key assigned to the new customer request and determine whether any existing hash key corresponds with the new hash key. If so, the system may associate the new batch of input observations with the corresponding hash key and update the corresponding hash key such that it is also configured to provide access to the new batch of input observations. If not, the system may generate a new stored task and assign the new hash key to it.

Abstract: The present disclosure discloses an unsupervised reinforcement learning method and apparatus based on Wasserstein distance. The method includes: obtaining a state distribution in a trajectory obtained with guidance of a current policy of an agent; calculating a Wasserstein distance between the state distribution and a state distribution in a trajectory obtained with another historical policy, and calculating a pseudo reward of the agent based on the Wasserstein distance, replacing a reward fed back from an environment in a target reinforcement learning framework with the pseudo reward, and guiding the current policy of the agent to keep a large distance from the other historical policy. The method uses Wasserstein distance to encourage an algorithm in an unsupervised reinforcement learning framework to obtain diverse policies and skills through training.

Abstract: A copy of a model comprising a plurality of trees is received, as is a copy of training set data comprising a plurality of training set examples. For each tree included in the plurality of trees, the training set data is used to determine which training set examples are classified as a given leaf. A blame forest is generated at least in part by mapping each training set item to the respective leaves at which it arrives.

Abstract: Systems and methods are disclosed for classifying objects by a machine learning (ML) model. The ML model includes one or more layer level classification models to generate classifications and uncertainty metrics in the classifications and a meta-model to generate a final classification and confidence based on the underlying classifications and uncertainty metrics. In some implementations, the ML model provides an object to be classified to one or more layer level classification models, and the layer level classification models generate a classification for the object and an uncertainty metric in the classification. The meta-model receives the classifications and uncertainty metrics from the one or more layer level classification models and generates the final classification and confidence in the final classification. The uncertainty metrics may also be output by the ML model or used to adjust the meta-model to improve the final classification and confidence.

Abstract: An accelerator with a modified kernel design for convolution processing in a Convolutional Neural Network (CNN) model is disclosed wherein the convolution execution time is reduced. A kernel structure is disclosed in the embodiment for the convolution operations that improves the overall performance of a CNN. Further, two loading units for weight and pixel loading reduce the latency involved in loading the network parameters into the processing elements. Moreover, a controller has been designed and included in the system architecture to aid the functioning of loading units efficiently.

Abstract: Systems and techniques are described for improving the evaluation of unstructured transaction data to, for example, recognize reoccurring data patterns or patterns of interest, predict future outcomes using historical indicators, identify attributes of interest, or evaluate likelihoods of certain conditions occurring. For example, a system can transform unstructured public record data obtained from multiple independent public data sources according to a hierarchical data model. The hierarchical data model can specify nodes within different data layers of a data hierarchy and classification labels corresponding to each of the nodes. In this way, the system can utilize data transformation techniques to permit the processing of information within unstructured transaction data that would have otherwise been impossible to perform without initially structuring the data according to the hierarchical data model.

Abstract: A method for controlling a physical process includes receiving an input dataset corresponding to the physical process. The method further includes determining a data model based on the input dataset. The data model includes a plurality of latent space variables of a machine learning model. The method also includes receiving a plurality of reference models corresponding to a plurality of classes. Each of the plurality of reference models includes a corresponding plurality of latent space variables. The method includes comparing the data model with each of the plurality of reference models to generate a plurality of distance metric values. The method further includes selecting a reference model among the plurality of reference models based on the plurality of distance metric values. The method also includes controlling the physical process based on the selected reference model.

Abstract: A computer-implemented method comprises training, using a validation set of input, a first classifier to predict when a second classifier will issue a classification error on a particular input, the first classifier generating a number of data buckets based on the validation set of input and populating a threshold lookup table for each data bucket based on a number of thresholds set for the second classifier during the training; storing each threshold lookup table in memory; obtaining a target error rate; obtaining a new input and running the new input through the first classifier, the first classifier selecting one of the data buckets for the new input; and selecting a threshold for the second classifier using the stored threshold lookup table for the selected data bucket and the target error rate.

Abstract: Devices and methods for processing detected signals at a detector using a processor are provided. The system involves (i) a data compressor that implements an algorithm for converting a set of data into a compressed set of data, (ii) a machine learning (ML) module coupled to the data compressor, the ML module transforming the compressed set of data into a vector and filtering the vector, (iii) a data encryptor coupled to the ML module that encrypts the filtered vector, and (iv) an integrity protection module coupled to the ML module, wherein the integrity protection module protects the integrity of the filtered vector.

Abstract: The invention relates to a water level prediction system for a dam. The system includes a water level prediction module which is configured to (a) receive time series data, which relates to a water level of the dam, in real-time; and (b) predict, in real-time, a future water level of the dam by processing the received time series data in one or more predictive models/formula(s)/algorithm(s). The one or more predictive models/formula(s)/algorithm(s) may include a recurrent neural network (RNN) or RNN model/algorithm which is configured/trained to predict, in real-time, a future water level of the dam by using the received time series data in the RNN or RNN model/algorithm. The water level prediction module may also include at least one statistical model/algorithm which is configured/trained to predict, in real-time, a future water level of the dam by using the received time series data in the statistical model/algorithm.

Abstract: A knowledge-based system under uncertainties and/or incompleteness, referred to as augmented knowledge base (AKB) is provided, including constructing, reasoning, analyzing and applying AKBs by creating objects in the form E?A, where A is a rule in a knowledgebase and E is a set of evidences that supports the rule A. A reasoning scheme under uncertainties and/or incompleteness is provided as augmented reasoning (AR).

Abstract: An agricultural data collection framework is provided in a system and method for tracking and managing livestock, and for analyzing animal conditions such as health, growth, nutrition, and behavior. The framework uses ultra-high frequency interrogation of RFID tags to collect individual animal data across multiple geographical locations, and incorporates artificial intelligence techniques to develop machine learning base models for statistical process controls around each animal for evaluating the animal condition. The framework provides a determination of normality at an individual animal basis or for a specific location, and generates alerts, predictions, and a targeted processing or application schedule for prioritizing and delivering resources when intervention is needed.