Abstract: A method for providing an activation signal for activating an actuator. The activation signal is ascertained as a function of an output signal of a neural network. The neural network includes a scaling layer. The scaling layer maps an input signal present at the input of the scaling layer onto an output signal present at the output of the scaling layer in such a way that this mapping corresponds to a projection of the input signal onto a predefinable value range, parameters being predefinable, which characterize the mapping.

Abstract: Embodiments of the present disclosure relate to a technique for training neural networks, such as a generative adversarial neural network (GAN), using a limited amount of data. Training GANs using too little example data typically leads to discriminator overfitting, causing training to diverge and produce poor results. An adaptive discriminator augmentation mechanism is used that significantly stabilizes training with limited data providing the ability to train high-quality GANs. An augmentation operator is applied to the distribution of inputs to a discriminator used to train a generator, representing a transformation that is invertible to ensure there is no leakage of the augmentations into the images generated by the generator. Reducing the amount of training data that is needed to achieve convergence has the potential to considerably help many applications and may the increase use of generative models in fields such as medicine.

Abstract: A method, system, and computer program product for explaining predictions made by black box time series models. The method may include identifying a black box time series model. The method may also include predicting one or more time instances using the black box time series model. The method may also include selecting a predicted time instance from the predicted data. The method may also include receiving training data for the black box time series model. The method may also include generating a set of white box time series models similar to the black box time series model. The method may also include selecting a preferred white box time series model. The method may also include analyzing behavior of the preferred white box time series model. The method may also include generating an explanation illustrating why the black box time series model forecasted the predicted time instance.

Abstract: A method comprising: receiving a primary training set comprising annotated data samples associated with one or more classes and annotated with class labels; constructing an auxiliary training set comprising at least some of the data samples, wherein each of the data samples is assigned at random to one of a set of identification classes, and annotated with an identification label associated with the identification class; at a training stage, train a machine learning model comprising a primary and auxiliary prediction heads, by: (i) training the primary prediction head on the primary training set to predict the class, and (ii) training the auxiliary prediction head on the auxiliary training set to predict the identification class, wherein an output layer of the machine learning model is configured to output a joint prediction which predicts the class label and is invariant to the identification label.

Abstract: Described are techniques for predictive microservice activation. The techniques include training a machine learning model using a plurality of sequences of coordinates, where the plurality of sequences of coordinates are respectively based upon a corresponding plurality of series of vectors generated from historical usage data for an application and its associated microservices. The techniques further include inputting a new sequence of coordinates representing a series of application operations to the machine learning model. The techniques further include identifying a predicted microservice for future utilization based on an output vector generated by the machine learning model. The techniques further include activating the predicted microservice prior to the predicted microservice being called by the application.

Abstract: The disclosure herein describes training a global model based on a plurality of data sets. The global model is applied to each data set of the plurality of data sets and a plurality of gradients is generated based on that application. At least one gradient quality metric is determined for each gradient of the plurality of gradients. Based on the determined gradient quality metrics of the plurality of gradients, a plurality of weight factors is calculated. The plurality of gradients is transformed into a plurality of weighted gradients based on the calculated plurality of weight factors and a global gradient is generated based on the plurality of weighted gradients. The global model is updated based on the global gradient, wherein the updated global model, when applied to a data set, performs a task based on the data set and provides model output based on performing the task.

Abstract: A processor-implemented neural network distributed processing method includes: obtaining a first operation cost of a neural network according to a distribution strategy based on a plurality of operation devices; generating an operation configuration corresponding to the neural network based on the obtained first operation cost; performing a reduction operation on the generated operation configuration; and processing an operation of the neural network based on a reduced operation configuration obtained by performing the reduction operation.

Abstract: The present invention provides a method and a device for estimating a value to be estimated associated with a specimen, by performing machine learning of a relationship between a value of an estimation object and an output corresponding thereto, based on an output from a chemical sensor with regard to a plurality of specimens for which specific values to be estimated are known, and using the result of the mechanical learning to estimate a specific value to be estimated on the basis of an output from the chemical sensor with regard to a given unknown specimen.

Abstract: Machine learning systems and methods for embedding attributed sequence data. The attributed sequence data includes an attribute data part having a fixed number of attribute data elements and a sequence data part having a variable number of sequence data elements. An attribute network module includes a feedforward neural network configured to convert the attribute data part to an encoded attribute vector having a first number of attribute features. A sequence network module includes a recurrent neural network configured to convert the sequence data part to an encoded sequence vector having a second number of sequence features. In use, the machine learning system learns and outputs a fixed-length feature representation of input attributed sequence data which encodes dependencies between different attribute data elements, dependencies between different sequence data elements, and dependencies between attribute data elements and sequence data elements within the attributed sequence data.

Abstract: There is provided with a data processing apparatus for detecting an object from an image using a hierarchical neural network. The data processing apparatus has parallel first and second neural networks. An obtaining unit obtains a table which defines different first and second portions. An operation unit performs calculation of the feature data of a third portion based on feature data of the first portion identified using the table and on a weighting parameter between first and second layers of the first neural network, and calculation of feature data of a fourth portion based on feature data of the second portion identified using the table and on a weighting parameter between the first and second layers of the second neural network.

Abstract: Methods for natural language semantic matching performed by training and using a Markov Network model are provided. The trained Markov Network model can be used to identify answers to questions. Training may be performed using question-answer pairs that include labels indicating a correct or incorrect answer to a question. The trained Markov Network model can be used to identify answers to questions from sources stored on a database. The Markov Network model provides superior performance over other semantic matching models, in particular, where the training data set includes a different information domain type relative to the input question or the output answer of the trained Markov Network model.

Abstract: In one aspect, the invention comprises a system and method for control of a transaction state system utilizing a distributed ledger. First, the system and method includes an application plane layer adapted to receive instructions regarding operation of the transaction state system. Preferably, the application plane layer is coupled to the application plane layer interface. Second, a control plane layer is provided, the control plane layer including an adaptive control unit, such as a cognitive computing unit, artificial intelligence unit or machine-learning unit. Third, a data plane layer includes an input interface to receive data input from one or more data sources and to provide output coupled to a decentralized distributed ledger, the data plane layer is coupled to the control plane layer. Optionally, the system and method serve to implement a smart contract on a decentralized distributed ledger.

Abstract: Some embodiments herein disclose intelligent priority evaluators configured to perform a method that prioritizes tasks submitted by various users, even if the tasks are similarly classified. The scheduling system can collect, calculate, and use various criteria to determine a reward score in order to prioritize one task over another, such as for dynamic scheduling purposes. This can be performed in addition to or as a replacement for receiving user designations of priority.

Abstract: Various embodiments include methods and devices for transforming a data block into weights for a neural network. Some embodiments may include training a first neural network of a cybernetic engram to reproduce the data block, and replacing the data block in memory with weights used by the first neural network to reproduce the data block.

Abstract: A method and system assists train a classifier model with a machine learning process. The method and system trains the classifier with a labeled training set and with an unlabeled training set. The method and system trains the classifier model to correctly classify data items that fall within a distribution of the labeled training set. The method and system trains the classifier to indicate a lack of confidence in classification for data items that do not fall within the distribution of the labeled training set.

Abstract: Disclosed is a batch normalization layer training method, which may be used in a neural network learning apparatus having limited operational processing capability and storage space. A batch normalization layer training method according to an embodiment of the present disclosure may perform batch normalization transform by setting the gradients of the standard deviation and the mean of the loss function to zero, and applying a normalized statistic value obtained from an initial neural network or a previous neural network to the gradient of the loss function. The neural network learning apparatus of the present disclosure may be connected or converged with an Artificial Intelligence module, an Unmanned Aerial Vehicle (UAV), a robot, an Augmented Reality (AR) apparatus, a Virtual Reality (VR), a 5G network service-related apparatus, etc.

Abstract: Reducing resource consumption of a database system and a machine learning (ML) system is described. Data is received from a ML application of a database system. The data includes a first inference call for a predicted response to the received data. The first inference call is a request to a ML model to generate one or more predictions for which a response is unknown. A ML model using the received data generates an output comprising the predicted response to the data. The output for future inference calls is cached in an inference cache so as to bypass the ML model. The generated output to the ML application is provided by the ML model. A second inference call is received which includes the data of the first inference call. The cached output is retrieved from the inference cache. The retrieving bypasses the ML model.

Abstract: Generally, the present disclosure is directed to systems and methods that perform adaptive optimization with improved convergence properties. The adaptive optimization techniques described herein are useful in various optimization scenarios, including, for example, training a machine-learned model such as, for example, a neural network. In particular, according to one aspect of the present disclosure, a system implementing the adaptive optimization technique can, over a plurality of iterations, employ an adaptive per coordinate clipping threshold to clip a current first moment of the coordinate to obtain a current update value that enables faster convergence for the machine-learned model when the noise in the stochastic gradients is heavy tailed.

Abstract: An artificial intelligence system for communicating predicted hours of operation to a client device. The system may include a processor in communication with a client device and a database; and a storage medium storing instructions.

Abstract: Disclosed is a system, method, and computer program product for implementing a log analytics method and system that can configure, collect, and analyze log records in an efficient manner. Machine learning-based classification can be performed to classify logs. This approach is used to group logs automatically using a machine learning infrastructure.