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.

Abstract: A learning device includes: a learning unit configured to read out feature amounts of learning data from a data memory and derive a branch condition for a node of a decision tree based on the feature amounts, to perform learning of the decision tree; and a discriminator configured to perform determining, in accordance with the branch condition, a node to which learning data is to be branched from the node corresponding to the branch condition. The learning unit is configured to, in parallel with processing of the discriminator reading out learning data at a specific node from the data memory via a first port of the data memory and performing the determining, read out, from the data memory via a second port, learning data at a node on which the discriminator is configured to perform determining subsequent to the specific node and derive the branch.

Abstract: The present disclosure provides a text processing method and device based on ambiguous entity words. The method includes: obtaining a context of a text to be disambiguated and at least two candidate entities represented by the text to be disambiguated; generating a semantic vector of the context based on a trained word vector model; generating a first entity vector of each of the at least two candidate entities based on a trained unsupervised neural network model; determining a similarity between the context and each candidate entity; and determining a target entity represented by the text to be disambiguated in the context.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for evaluating reinforcement learning policies. One of the methods includes receiving a plurality of training histories for a reinforcement learning agent; determining a total reward for each training observation in the training histories; partitioning the training observations into a plurality of partitions; determining, for each partition and from the partitioned training observations, a probability that the reinforcement learning agent will receive the total reward for the partition if the reinforcement learning agent performs the action for the partition in response to receiving the current observation; determining, from the probabilities and for each total reward, a respective estimated value of performing each action in response to receiving the current observation; and selecting an action from the pre-determined set of actions from the estimated values in accordance with an action selection policy.

Abstract: Example aspects of the present disclosure are directed to systems and methods for learning classification models which satisfy constraints such as, for example, constraints that can be expressed as a predicted positive rate or negative rate on a subset of the training dataset. In particular, through the use of quantile estimators, the systems and methods of the present disclosure can transform a constrained optimization problem into an unconstrained optimization problem that is solved more efficiently and generally than the constrained optimization problem. As one example, the unconstrained optimization problem can include optimizing an objective function where a decision threshold of the classification model is expressed as an estimator of a quantile function on the classification scores of the machine-learned classification model for a subset of the training dataset at a desired quantile.

Abstract: This application discloses a method and an apparatus for training a classification model. The method includes obtaining a training sample, the training sample including a training parameter and a true classification corresponding to the training parameter and preforming classification training on an initial classification model by using the training parameter, to obtain a predicted classification. The method also includes determining a residual between the true classification and the predicted classification according to a gradient loss function of the initial classification model, the gradient loss function comprising a distance factor representing a distance between a first category and a second category, the first category being a category to which the predicted classification belongs, and the second category being a category to which the true classification belongs. The method further includes modifying the initial classification model according to the residual to obtain a final classification model.

Abstract: Methods and apparatuses are described for automated predictive analysis of user interactions to determine a modification based upon competing classification models. A server computing device receives first encoded text for prior user interactions and trains a plurality of classification models using the first text. The server determines a prediction cost for each of the models based upon the training. The server receives second encoded text for a current user interaction and executes the trained models using the second text to generate a prediction vector for each model that maximizes user engagement. The server selects one of the models based upon the prediction vectors, identifies a communication feature of the model, generates a user interaction modification, and transmits the user interaction modification to a client computing device.

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: Example implementations described herein involve an interface for calculating and displaying missing links for data represented as a bipartite network, along with novel methods for improving link prediction algorithms in the related art. Through example implementations described herein, the accuracy of link prediction algorithms can be improved upon, thereby providing the user with a more accurate understanding of the data in the bipartite network.