Abstract: One or more systems, devices, computer program products, and/or computer-implemented methods provided herein relate to accurate anomaly detection in images using patched features. According to an embodiment, an extraction component can extract multiple layers of features from one or more patches of an image using a pretrained convolutional neural network (CNN). A feature mapping component can concatenate the features from the multiple layers to generate a tensor feature map comprising a one-dimensional feature vector for respective patches. A cropping component can perform center cropping on the tensor feature map. A calculation component can calculate a distance to a feature distribution mean for respective patches.

Abstract: A computer-implemented method is provided for learning with incomplete data in which some of entries are missing. The method includes acquiring an incomplete set of covariates x including incomplete features {tilde over (x)} and an incomplete pattern m indicating missing entries of the incomplete set of covariates {tilde over (x)}. The method further includes obtaining, by a hardware processor, a predictive distribution p?(y|x) of an outcome y by using the incomplete set of covariates x and a parameter ?, the parameter ? being unknown. A learning of the parameter ? includes performing a maximization by maximizing a stochastically approximated conditional evidence lower bound.

Abstract: A computerized machine learning anomaly detection model trained on a plurality of samples of one or more source domains (optionally, one or more source domains and the target domain) is accessed. Using online deep sets, one or more domain vectors are computed for each target domain sample at an observation point, each target domain sample corresponding to a given target domain, where the one or more domain vectors represent a similarity and difference among the source and target domains. The target domain sample is processed using the anomaly detection model trained on the plurality of samples of the source to generate an anomaly score, the processing being based on the computed one or more domain vectors.

Abstract: Various embodiments train a prediction model for predicting a label to be allocated to a prediction target explanatory variable set. In one embodiment, one or more sets of training data are acquired. Each of the one or more sets of training data includes at least one set of explanatory variables and a label allocated to the at least one explanatory variable set. A plurality of explanatory variable subsets is extracted from the at least one set of explanatory variables. A prediction model is trained utilizing the training data. The plurality of explanatory variable subsets is reflected on a label predicted by the prediction model to be allocated to a prediction target explanatory variable set with each of the plurality of explanatory variable subsets weighted respectively.

Abstract: A computer-implemented method is presented for discovering new material candidates from a chemical database. The method includes extracting a feature vector from a chemical formula, learning a prediction model for predicting property values from the feature vector with a sparse kernel model employing the chemical database, selecting an existing material from a list of existing materials sorted in descending order based on the predicted property values by the prediction model learned in the learning step, selecting a basis material from a list of basis materials sorted in descending order of absolute reaction magnitudes to the selected existing material, and generating the new material candidates as variants of the selected existing material with consideration of the selected basis material.

Abstract: A method, a computer program product, and a system of adversarial semi-supervised one-shot training using a data stream. The method includes receiving a data stream based on an observation, wherein the data stream includes unlabeled data and labeled data. The method also includes training a prediction model with the labeled data using stochastic gradient descent based on a classification loss and an adversarial term and training a representation model with the labeled data and the unlabeled data based on a reconstruction loss and the adversarial term. The adversarial term is a cross-entropy between the middle layer output data from the models. The classification loss is a cross-entropy between the labeled data and an output from the prediction model. The method further includes updating a discriminator with middle layer output data from the prediction model and the representation model and based on a discrimination loss, and discarding the data stream.

Abstract: A computer-implemented method is provided for machine prediction. The method includes forming, by a hardware processor, a Convolutional Dynamic Boltzmann Machine (C-DyBM) by extending a non-convolutional DyBM with a convolutional operation. The method further includes generating, by the hardware processor using the convolution operation of the C-DyBM, a prediction of a future event at time t from a past patch of time-series of observations. The method also includes performing, by the hardware processor, a physical action responsive to the prediction of the future event at time t.

Abstract: A method is provided for clustering data elements to extract specific patterns. The method specifies some data elements with a uniform distribution as a mini-batch and performs a single-pass cluster initialization by selecting a respective data element from the mini-batch as a respective initial cluster center to obtain cluster centers for clusters. The method assigns each data element in the mini-batch to a closest cluster by calculating a distance between each of the data elements in the mini-batch and each of the clusters. The method assigns k-minimum new centers by calculating an averaged distance to each data element in a same cluster. The method repeats the specifying step and the assigning steps responsive to a dissatisfaction of loop stop criteria which is based on distances between the centers and the K-minimum new centers. The method outputs a cluster id sequence responsive to a satisfaction of the loop stop criteria.

Abstract: A computer-implemented method for training a lattice layer in a Deep Lattice Network includes preparing parameters of vertices, each of the parameters corresponding to each vertex of a subdivided unit hypercube defined by subdividing an S-dimensional unit hypercube by a s predetermined number k with k vertices and defining each parameter by identifying one vertex in a specific order, identifying a first set of vertices that appear before the identified vertex in the specific order, identifying a second set of vertices that appear before the identified vertex in the specific order, defining a lower bound as a maximum value among values of vertices in the first set of vertices, defining an upper bound as a minimum value among values of vertices in the second set of vertices, and defining the parameter of the identified vertex based on the lower bound, the upper bound, and a parameter corresponding to the identified vertex.

Abstract: Methods and systems are provided for obtaining cleaned sequences showing trajectories of movement of a center of gravity and for estimating a biometric information pattern or value of a target. One of the methods includes removing noises from initial sequences showing trajectories of movement of a center of gravity to obtain the cleaned sequences. Another one of the methods includes reading cleaned sequences of the target into a memory, extracting features from the cleaned sequences, and estimating a biometric information pattern or value of the target from the extracted features, using a classification or regression model of biometric information patterns or values. The biometric information pattern may be a pattern derived from respiratory or circulatory organs of a target.

Abstract: A computer-implemented method for updating hidden states in a recurrent neural network (RNN) to predict future data from multivariate time-series data with irregular time intervals is provided including inputting, for each of time steps at observations, observation data at a current time step in the multivariate time-series data to the RNN, for each of the time steps: subdividing a time interval between a previous time step and the current time step by a predetermined number, for each of subdivided time steps calculating a first element of the hidden state at a current subdivided time step using ODE-RNNs, and calculating a second element of the hidden state at the current subdivided time step using the last updated hidden state and a hidden state at the previous time step so that the last updated hidden state is decayed to be close to the hidden state at the previous time step.

Abstract: An information processing apparatus includes a history acquisition section configured to acquire history data including a history indicating that a plurality of selection subjects have selected selection objects; a learning processing section configured to allow a choice model to learn a preference of each selection subject for a feature and an environmental dependence of selection of each selection object in each selection environment using the history data, where the choice model uses a feature value possessed by each selection object, the preference of each selection subject for the feature, and the environmental dependence indicative of ease of selection of each selection object in each of a plurality of selection environments to calculate a selectability with which each of the plurality of selection subjects selects each selection object; and an output section configured to output results of learning by the learning processing section.

Abstract: A computer-implemented method for reconstructing time series data including irregular time intervals and missing values to predict future data from the time series data using a Recurrent Neural Network (RNN) is provided including obtaining irregular time series data X={x1, . . . , xt, . . . , xT} and time interval data ?={?1, . . . , ?t, . . . , ?T}, where xt is a D-dimensional feature vector, T is a total number of observations, ?t is a D-dimensional time interval vector, and a d-th element ?td of ?t represents a time interval from a last observation, replacing missing values in xt with imputed values using an imputation to obtain {tilde over (x)}t, rescaling data of the time interval ?t to obtain rescaled time interval data ?(?t) by calculating ?(?t)=? log(e+ max(0,??t+b?))+b?, where W?, W?, b?, b? are network parameters of a neural network and e is Napier's constant, and multiplying {tilde over (x)}t by ?(?t) to obtain {circumflex over (x)}t as regular time series data for input of the RNN.

Abstract: A computer-implemented method for computing an objective function of discriminative inference with generative models with incomplete data in which some of entries are missing is provided including acquiring an incomplete set of covariates x including incomplete features {tilde over (x)} and an incomplete pattern m indicating missing entries of the incomplete features {tilde over (x)} and computing a predictive distribution p?(y|x) of an outcome y by using the incomplete set of covariates x and a parameter ?, the parameter ? being unknown. Learning of the parameter ? is performed by minimizing an objective function (?):=?ln p?(y|x)=ln p?({tilde over (x)}|m)?ln p?(y,x|m), and the objective function (?) is bounded with a difference between a marginal evidence upper bound MEUBO and a joint evidence lower bound JELBO, where ln p?({tilde over (x)}|m)?MEUBO and ln p?(y,{tilde over (x)}|m)?JELBO.

Abstract: Methods and systems are provided for obtaining cleaned sequences showing trajectories of movement of a center of gravity and for estimating a biometric information pattern or value of a target. One of the methods includes removing noises from initial sequences showing trajectories of movement of a center of gravity to obtain the cleaned sequences. Another one of the methods includes reading cleaned sequences of the target into a memory, extracting features from the cleaned sequences, and estimating a biometric information pattern or value of the target from the extracted features, using a classification or regression model of biometric information patterns or values. The biometric information pattern may be a pattern derived from respiratory or circulatory organs of a target.

Abstract: A computer-implemented method is provided for predicting a medical event time. The method includes receiving an electronic health record (EHR) including a plurality of pairs of observation variables and corresponding timestamps. Each of the plurality of pairs include a respective observation variable and a respective corresponding timestamp. The method further includes converting the EHR into a K-dimensional vector representing a cumulative-stay time at a finite number of patient medical states, the patient medical states being determined by values of the observation variables. The method also includes processing, by a hardware processor, the K-dimensional vector using a medical event time prediction model to output a prediction of a medical event time. The medical event time prediction model has been configured through training to receive and process K-dimensional vectors converted from past EHRs to output predicted medical event times.

Abstract: A method, a computer program product, and a system of adversarial semi-supervised one-shot training using a data stream. The method includes receiving a data stream based on an observation, wherein the data stream includes unlabeled data and labeled data. The method also includes training a prediction model with the labeled data using stochastic gradient descent based on a classification loss and an adversarial term and training a representation model with the labeled data and the unlabeled data based on a reconstruction loss and the adversarial term. The adversarial term is a cross-entropy between the middle layer output data from the models. The classification loss is a cross-entropy between the labeled data and an output from the prediction model. The method further includes updating a discriminator with middle layer output data from the prediction model and the representation model and based on a discrimination loss, and discarding the data stream.

Abstract: A method is presented for estimating conditional quantile values of a response variable distribution. The method includes acquiring training data with first values and second values, a list of quantile levels, a lower bound of the second values, and an upper bound of the second values and transforming the list of quantile levels into a tree-structure by recursively dividing an interval in a range between 0 and 1 into sub-intervals by using the list of quantile levels such that each node of the tree-structure is associated with a tuple of three quantile levels. The method further includes training a neural network for each node in the tree-structure and estimating a relative quantile value for each of the first values by using a first estimated quantile value as a lower bound and a second estimated quantile value as an upper bound.

Abstract: A computer-implemented method of predicting a risk of an accident is disclosed. The method includes computing an anomaly score based on sensor data to obtain a series of anomaly scores. The method also includes processing the anomaly score to limit a processed anomaly score below a predetermined value. The method further includes calculating an accident risk score at time of prediction by using a series of processed anomaly scores up to the time of the prediction. The method includes further outputting a prediction result based on the accident risk score.

Abstract: Described are techniques for fair anomaly detection. The techniques include generating an anomaly detection model based on a Gaussian distribution of historical data, a mean vector of the Gaussian distribution, and a precision matrix of the Gaussian distribution. The mean vector and the precision matrix can be generated by reducing a function below a threshold, where the function can include the Gaussian distribution, a first regularization term configured to generate similar anomaly scores for inputs with similar fair features and independent of unfair features, and a second regularization term configured to generate similar anomaly localization scores for the inputs with the similar fair features and independent of the unfair features. The techniques further include inputting a new data to the anomaly detection model and generating an anomaly score and an anomaly localization score associated with the new data based on the Gaussian distribution, the mean vector, and the precision matrix.