Abstract: A computer-implemented method includes monitoring, by a computing device, sensor data during gameplay of a sporting event; determining, by the computing device, predictive factors associated with a target based on the monitoring the sensor data; determining, by the computing device, a real-time region of effectiveness for the target based on the predictive factors and training data identifying historical effectiveness of the target; and outputting, by the computing device, the real-time region of effectiveness for displaying the real-time region of effectiveness around the target.

Abstract: Systems and methods for spatial graph convolutions in accordance with embodiments of the invention are illustrated. One embodiment includes a method for predicting characteristics for molecules, wherein the method includes performing a first set of graph convolutions with a spatial graph representation of a set of molecules, wherein the first set of graph convolutions are based on bonds between the set of molecules, performing a second set of graph convolutions with the spatial graph representation, wherein the second set of graph convolutions are based on at least a distance between each atom and other atoms of the set of molecules, performing a graph gather with the spatial graph representation to produce a feature vector, and predicting a set of one or more characteristics for the set of molecules based on the feature vector.

Abstract: Techniques are described that extend supervised machine-learning algorithms for use with semi-supervised training. Random labels are assigned to unlabeled training data, and the data is split into k partitions. During a label-training iteration, each of these k partitions is combined with the labeled training data, and the combination is used train a single instance of the machine-learning model. Each of these trained models are then used to predict labels for data points in the k?1 partitions of previously-unlabeled training data that were not used to train of the model. Thus, every data point in the previously-unlabeled training data obtains k?1 predicted labels. For each data point, these labels are aggregated to obtain a composite label prediction for the data point. After the labels are determined via one or more label-training iterations, a machine-learning model is trained on data with the resulting composite label predictions and on the labeled data set.

Abstract: A modeling system trains a recurrent machine-learned model by determining a latent distribution and a prior distribution for a latent state. The parameters of the model are trained based on a divergence loss that penalizes significant deviations between the latent distribution the prior distribution. The latent distribution for a current observation is a distribution for the latent state given a value of the current observation and the latent state for the previous observation. The prior distribution for a current observation is a distribution for the latent state given the latent state for the previous observation independent of the value of the current observation, and represents a belief about the latent state before input evidence is taken into account.

Abstract: Various implementations disclosed herein include devices, systems, and methods for training of an action determining component of a computer character. In some implementations, actions are taken by the character in a 3D environment according to an action determining component of the character, where the character is rewarded or penalized for interactions associated with an object/concept in the 3D environment according to an assigned object/concept reward or penalty. In some implementations, the reward or the penalty assigned to the object/concept is modified, and the character is then rewarded or penalized for interactions associated with the object/concept according to the modified reward or the modified penalty. The action determining component of the character is trained using a reinforcement learning technique that accounts for rewards or penalties obtained by virtual character for interactions associated with the object/concept.

Abstract: Apparatus and methods for training a neural network accelerator using quantized precision data formats having outlier values are disclosed, and in particular for storing activation values from a neural network in a compressed format for use during forward and backward propagation training of the neural network. In certain examples of the disclosed technology, a computing system is configured to perform forward propagation for a layer of a neural network to produced first activation values in a first block floating-point format. In some examples, activation values generated by forward propagation are converted by the compressor to a second block floating-point format having a narrower numerical precision than the first block floating-point format. Outlier values, comprising additional bits of mantissa and/or exponent are stored in ancillary storage for subset of the activation values. The compressed activation values are stored in the memory, where they can be retrieved for use during back propagation.

Abstract: Methods and systems for determining an optimized setting for one or more process parameters of a machine learning training process. One of the methods includes processing a current network input using a recurrent neural network in accordance with first values of the network parameters to obtain a current network output, obtaining a measure of the performance of the machine learning training process with an updated setting defined by the current network output, and generating a new network input that comprises (i) the updated setting defined by the current network output and (ii) the measure of the performance of the training process with the updated setting defined by the current network output.

Abstract: Some embodiments of the invention provide a machine-trained method that selects an output from a plurality of outputs by processing an input. The method uses layers of machine-trained processing nodes to process the input to produce a multi-dimensional codeword. The method generates a set of affinity scores with each affinity score identifying the proximity of the produced codeword to a codeword in a first set of previously defined codewords. The method compares the set of affinity scores generated for the produced codeword with sets of affinity scores previously generated for the first-set codewords that express the proximity of the first-set codewords to a second set of codewords. The method identifies the first-set codeword that has the affinity score set that best matches the affinity score set generated for the produced codeword. The method selects the associated output of the identified first-set codeword as the output of the network.

Abstract: Systems, methods, and apparatuses for detecting and identifying anomalous data in an input data set are provided.

Abstract: Mechanisms are provided to implement a bias identification engine that identifies bias in the operation of a trained cognitive computing system. A bias risk annotator is configured to identify a plurality of bias triggers in inputs and outputs of the trained cognitive computing system based on a bias risk trigger data structure that specifies terms or phrases that are associated with a bias. An annotated input and an annotated output of the trained cognitive computing system is received and processed by the bias risk annotator to determine if they comprise a portion of content that contains a bias trigger. In response to at least one of the annotated input or annotated output comprising a portion of content containing a bias trigger a notification is transmitted, to an administrator computing device, that specifies the presence of bias in the operation of the trained cognitive computing system.

Abstract: Parallel training of a machine learning model on a computerized system may be provided. Computing tasks can be assigned to multiple workers of a system. A method may include accessing training data. A parallel training of the machine learning model can be started based on the accessed training data, so as for the training to be distributed through a first number K of workers, K>1. Responsive to detecting a change in a temporal evolution of a quantity indicative of a convergence rate of the parallel training (e.g., where said change reflects a deterioration of the convergence rate), the parallel training of the machine learning model is scaled-in, so as for the parallel training to be subsequently distributed through a second number K? of workers, where K>K??1. Related computerized systems and computer program products may be provided.

Abstract: An information processing device generates a prediction output corresponding to input data. The information processing device includes input-node specification processor circuitry, based on the input data, configured to specify input nodes corresponding to the input data and each located on a corresponding one of layers from beginning to end of the learning tree structured, reliability-index acquisition processor circuitry configured to acquire a reliability index obtained through the predetermined learning processing and indicating prediction accuracy, output-node specification processor circuitry, based on the reliability index acquired by the reliability-index acquisition processor circuitry configured to specify, from the input nodes corresponding to the input data, an output node that is the basis of the generation of a prediction output, and prediction-output generation processor circuitry configured to generate a prediction output.

Abstract: Systems and methods use deep, convolutional neural networks over exponentially long history windows to learn alphabets for context tree weighting (CTW) for prediction. Known issues of depth and breadth in conventional context tree weighting predictions are addressed by the systems and methods. To deal with depth, the history can be broken into time windows, permitting the ability to look exponentially far back while having less information the further one looks back. To deal with breadth, a deep neural network classifier can be used to learn to map arbitrary length histories to a small output symbol alphabet. The sequence of symbols produced by such a classifier over the history windows would then become the input sequence to CTW.

Abstract: Systems and methods for spatial graph convolutions in accordance with embodiments of the invention are illustrated. One embodiment includes a method for predicting characteristics for molecules, wherein the method includes performing a first set of graph convolutions with a spatial graph representation of a set of molecules, wherein the first set of graph convolutions are based on bonds between the set of molecules, performing a second set of graph convolutions with the spatial graph representation, wherein the second set of graph convolutions are based on at least a distance between each atom and other atoms of the set of molecules, performing a graph gather with the spatial graph representation to produce a feature vector, and predicting a set of one or more characteristics for the set of molecules based on the feature vector.

Abstract: Herein, horizontally scalable techniques efficiently configure machine learning algorithms for optimal accuracy and without informed inputs. In an embodiment, for each particular hyperparameter, and for each epoch, a computer processes the particular hyperparameter. An epoch explores one hyperparameter based on hyperparameter tuples. A respective score is calculated from each tuple. The tuple contains a distinct combination of values, each of which is contained in a value range of a distinct hyperparameter. All values of a tuple that belong to the particular hyperparameter are distinct. All values of a tuple that belong to other hyperparameters are held constant. The value range of the particular hyperparameter is narrowed based on an intersection point of a first line based on the scores and a second line based on the scores. A machine learning algorithm is optimally configured from repeatedly narrowed value ranges of hyperparameters. The configured algorithm is invoked to obtain a result.

Abstract: A method for training a machine learning model includes: receiving, by a computer system including a processor and memory, a training data set including imbalanced data; computing, by the computer system, a label density fX(x) in the training data set, computing, by the computer system, a weight function w(x) including a term that is inversely proportional to the label density; weighting, by the computer system, a loss function (x, {circumflex over (x)}) in accordance with the weight function to generate a weighted loss function w(x, {circumflex over (x)}); training, by the computer system, a continuous machine learning model in accordance with the training data set and the weighted loss function w(x, {circumflex over (x)}); and outputting, by the computer system, the trained continuous machine learning model.

Abstract: Systems and methods for spatial graph convolutions in accordance with embodiments of the invention are illustrated. One embodiment includes a method for predicting characteristics for molecules, wherein the method includes performing a first set of graph convolutions with a spatial graph representation of a set of molecules, wherein the first set of graph convolutions are based on bonds between the set of molecules, performing a second set of graph convolutions with the spatial graph representation, wherein the second set of graph convolutions are based on at least a distance between each atom and other atoms of the set of molecules, performing a graph gather with the spatial graph representation to produce a feature vector, and predicting a set of one or more characteristics for the set of molecules based on the feature vector.

Abstract: Embodiments of the present invention are directed to a computer-implemented method for multiscale representation of input data. A non-limiting example of the computer-implemented method includes a processor receiving an original input. The processor downsamples the original input into a downscaled input. The processor runs a first convolutional neural network (“CNN”) on the downscaled input. The processor runs a second CNN on the original input, where the second CNN has fewer layers than the first CNN. The processor merges the output of the first CNN with the output of the second CNN and provides a result following the merging of the outputs.

Abstract: A method in which user information is transmitted from at least one data source to a processing unit of a learning device. The user information is used, by the processing unit via a machine learner, to generate at least one user model. The at least one user model is adapted via an adaptation of parameters used by the at least one machine learner to generating the at least one user model. The parameters, used by the at least one machine learner for generating the at least one user model, are adapted as a function of at least one predefined rule. The user model generated on the basis of the adapted parameters is used to personalize at least one terminal.

Abstract: An example operation may include one or more of generating, by a training participant client comprising a training dataset, a plurality of transaction proposals that each correspond to a training iteration for machine learning model training related to stochastic gradient descent, the machine learning model training comprising a plurality of training iterations, the transaction proposals comprising a gradient calculation performed by the training participant client, a batch from the private dataset, a loss function, and an original model parameter, receiving, by one or more endorser nodes of peers of a blockchain network, the plurality of transaction proposals, and evaluating each transaction proposal.