Abstract: Embodiments for recommending actions to improve machine learning predictions by a processor. One or more recommended actions may be linked to one or more features that influence a predicted outcome of a prediction model of a machine learning operation. One or more features having one or more negative factors that negatively impact the predicted outcome of the prediction model may be determined and selected. One or more of the linked recommended actions may be applied to one or more of the features to mitigate a negative impact upon the predicted outcome of the prediction model.

Abstract: A system and approach for deriving data for a constrained environment of a controller such as, for example, an embedded device. The controller may incorporate a processor and a memory connected to the processor. The memory may have a constrained capacity. The memory may contain an extensible set of rules for deriving additional semantic information from available information at the embedded device. The processor and the memory with the extensible set of rules may constitute a semantic rule engine. The semantic rule engine may apply the extensible set of rules to the available information to derive the additional semantic information.

Abstract: Systems and methods disclosed herein are directed to blockchain-based training data management systems and methods for trusted improvements of models. Embodiments provide for the generation of metadata and smart contracts associated with certain data, using a blockchain to store the generated metadata and smart contracts, and curating training data for the improvement of the models utilizing the generated metadata and smart contract stored in the blockchain.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: inputs of emotion time series data of a user and environmental factor data from one or more data collection device for a user assistance service. A baseline emotion time series is generated and an environmental factor that is likely to have affected changes in state of emotion on a subject is identified by regression analysis. An emotion time series model for the identified environmental factor is produced and prediction of a path to attain a target state of emotion at a certain time in the future is made. Recommendation to achieve the target state of emotion is produced based on the predicted path.

Abstract: Disclosed herein is a method for facilitating analysis of a model. Accordingly, the method may include receiving, using a communication device, a model data associated with a model from a user device, assessing, using a processing device, the model data, identifying, using the processing device, a field associated with the model based on the assessing, analyzing, using the processing device, the field based on the identifying of the field, identifying, using the processing device, a related field associated with the field based on the analyzing of the field, analyzing, using the processing device, the related field based on the model, generating, using the processing device, a notification based on the analyzing of the related field, transmitting, using the communication device, the notification to the user device, and storing, using a storage device, the model data and the model.

Abstract: Some embodiments provide a method for training a machine-trained (MT) network. The method uses a first set of inputs to train parameters of the MT network according to a set of hyperparameters that define aspects of the training. The method uses a second set of inputs to validate the MT network as trained by the first set of inputs. Based on the validation, the method modifies the hyperparameters for subsequent training of the MT network, wherein the hyperparameter modification is constrained to prevent overfitting of the modified hyperparameters to the second set of inputs.

Abstract: Example machine learning (ML) methods and systems for characterizing corn growth efficiency (CGE), and generating field management recommendations based on CGE values are disclosed. An example computing system includes one or more processors, and storage media. The media storing an ML model trained using a training agronomic data set labeled with one or more known CGE values corresponding to one or more trial agricultural fields. The media further storing instructions that, when executed, cause the system to: obtain a production agronomic data set corresponding to a target agricultural field; determine one or more input feature vectors based on the production agronomic data set; process the one or more input feature vectors, with the ML model, to generate one or more predicted CGE values for one or more portions of the target agricultural field; and provide the one or more predicted CGE values as an output.

Abstract: A method and system for incorporating regression into a Stacked Auto Encoder utilizing deep learning based regression technique that enables joint learning of parameters for a regression model to train the SAE for a regression problem. The method comprises generating a regression model for the SAE for solving the regression problem, wherein regression model is formulated as a non-convex joint optimization function for an asymmetric SAE. The method further comprises reformulating the non-convex joint optimization function as an Augmented Lagrangian formulation in terms of a plurality of proxy variables and a plurality of hyper parameters. The method comprises splitting the Augmented Lagrangian formulation into sub-problems using Alternating Direction Method of Multipliers and jointly learning parameters for the regression model to train the SAE for the regression problem. The learned weights enable estimating the unknown target values.

Abstract: A device, system, and method is provided for storing a sparse neural network. A plurality of weights of the sparse neural network may be obtained. Each weight may represent a unique connection between a pair of a plurality of artificial neurons in different layers of a plurality of neuron layers. A minority of pairs of neurons in adjacent neuron layers are connected in the sparse neural network. Each of the plurality of weights of the sparse neural network may be stored with an association to a unique index. The unique index may uniquely identify a pair of artificial neurons that have a connection represented by the weight. Only non-zero weights may be stored that represent connections between pairs of neurons (and zero weights may not be stored that represent no connections between pairs of neurons).

Abstract: Systems and methods for increasing the training value of input training datasets are described herein. In an embodiment, a server computer receives a plurality of input training datasets, each of the input training datasets comprising values for a plurality of parameters, a value indicating whether failure has occurred, and another value indicating the time of failure or the time of observation if no failure has occurred. For each input training dataset, the server computer generates a plurality of month-specific training datasets, each of which comprising a first value indicating a number of previous months where failure has not occurred and a second value indicating whether failure occurred during a month corresponding to the month-specific training data. The server computer trains a machine learning model using the plurality of month-specific training datasets.

Abstract: Systems and methods for computer-implemented evaluation of a performance are provided. In a first aspect, a computer-implemented method of evaluating an interaction generates a first temporal record of first behavior features exhibited by a first entity during an interaction between a first entity and a second entity. A second temporal record is generated including second behavior features exhibited by a second entity during an interaction with a first entity. A determination is made that a first feature of a first temporal record is associated with a second feature of a second temporal record. The length of time that passes between the first feature and second feature is evaluated, and a determination is made that the length of time satisfies a temporal condition. A co-occurrence record associated with a first feature and a second feature is generated and included in a co-occurrence record data-structure.

Abstract: The example embodiments are directed to a continuously expanding cross-domain featuring engineering system. In one example, a method may include one or more of storing predictive features in a cross-domain data store, the predictive features previously used in machine learning modeling in a plurality of different domains, receiving data of an asset included in a target domain and information about an evaluation attribute associated with the asset in the target domain, determining a predictive feature in the received data based on a previously used predictive feature stored in the cross-domain data store which is associated with a machine learning model in a different domain and the evaluation attribute, and outputting the determined predictive feature for display via a user interface.

Abstract: High dynamic range, high class count, high input rate winner-take-all on neuromorphic hardware is provided. In some embodiments, a plurality of thermometer codes are received by a neurosynaptic core. The plurality of thermometer codes are split into a plurality of intervals. One of the plurality of intervals is selected. A local maximum is determined within the one of the plurality of intervals. A global maximum is determined based on the local maximum.

Abstract: A method for performing learning in a dissipative learning network is described. The method includes determining a trajectory for the dissipative learning network and determining a perturbed trajectory for the dissipative learning network based on a plurality of target outputs. Gradients for a portion of the dissipative learning network are determined based on the trajectory and the perturbed trajectory. The portion of the dissipative learning network is adjusted based on the gradients.

Abstract: Provided are a system and methodology for iteratively transforming data, as between multiple sets thereof, that account for underlying data generation sources and bases. Doing so, via normalization of the data, enables uniformity of interpretation and presentation of the data no matter the machine learning model that produced the data.

Abstract: Methods and systems for training a neural network (NN)-based climate forecasting model on a pre-processed multi-model ensemble of global climate simulation data from a plurality of global climate simulation models (GCMs), are disclosed. The methods and systems perform steps of determining a common spatial scale and a common temporal scale for the multi-model ensemble of global climate simulation data; spatially re-gridding the multi-model ensemble to the common spatial scale; temporally homogenizing the multi-model ensemble to the common temporal scale; augmenting the spatially re-gridded, temporally homogenized multi-model ensemble with synthetic simulation data generated from the spatially re-gridded, temporally homogenized multi-model ensemble; and training the NN-based climate forecasting model using the spatially re-gridded, temporally homogenized, and augmented multi-model ensemble of global climate simulation data.

Abstract: Aspects of the subject disclosure may include, for example, obtaining a plurality of historical inputs, obtaining a plurality of historical outputs, applying a piecewise linear regression, deep learning algorithm to at least the plurality of historical inputs and the plurality of historical outputs to generate a plurality of predicted inputs, applying a plurality of weightings to the plurality of predicted inputs to generate a plurality of predicted weighted inputs, and applying at least one simulation to the plurality of predicted weighted inputs to generate a plurality of predicted weighted outputs. Other embodiments are disclosed.

Abstract: Described is a system for specifying control of a device based on a Bayesian network model. The system includes a Bayesian neuromorphic compiler having a network composition module having probabilistic computation units (PCUs) arranged in a hierarchical composition containing multi-level dependencies. The Bayesian neuromorphic compiler receives a Bayesian network model as input and produces a spiking neural network topology and configuration that implements the Bayesian network model. The network composition module learns conditional probabilities of the Bayesian network model. The system computes a conditional probability and controls a device based on the computed conditional probability.

Abstract: A design application is configured to perform a system-level optimization of a collection of system components. The design application iteratively executes a multi-objective solver to optimize structural and functional relationships between the system components in order to meet global design criteria and generate a system design. The design application initializes the design process by extracting from a knowledge base system templates having taxonomic, structural, or functional attributes relevant to the system design. The design application generates the knowledge base by mining taxonomic, structural, and functional relationships from a corpus of engineering texts.

Abstract: A device for estimating a cause of an anomaly comprises: a detection unit to detect an anomaly in a detection target based on a learner trained on first numerical vectors obtained from a detection target when the detection target is under a normal condition and second numerical vectors to be obtained from the detection target at multiple time; and a first computing unit to compute, for each metric of a second numerical vector from which an anomaly has been detected, as information for estimating a metric of cause of the anomaly, a value obtained by subtracting, from a value of the metric, an average of the metric in the first numerical vectors, and dividing a result of the subtracting by standard deviation of the metric in the first numerical vectors. This device supports estimation of the cause of an anomaly detected in a target object for detecting an anomaly.