Abstract: A computer-implemented process for training a prediction model for survival analysis includes the following operations. A batch of data is elected from a training dataset representing a plurality of individuals. A curve representing a survival rate of a group of individuals within the batch over a period of time is generated using a non-parametric statistical function and for the batch of data. Individual survival functions for each individual within the batch are estimated using the prediction model. An average survival function is generated from the individual survival functions. A calibration loss is generated using the curve representing the survival rate and the average survival function. Weight of a neural network including the prediction model are updated based upon a total loss including the calibration loss.

Abstract: A method, which trains a neural network to perform an analysis that satisfies average calibration, includes a processor manipulating a data set that includes an outcomes vector and a set of feature vectors, each of which corresponds to one of the outcomes in the outcomes vector. The processor repeatedly: selects a subset of the set of feature vectors; generates a distribution vector for a subset of the outcomes vector that corresponds to the subset of the set of feature vectors; produces a prediction vector by running the neural network on the subset of the set of feature vectors; calculates a Bregman divergence between the distribution vector and a scoring distribution vector of the prediction vector; and updates weights of the neural network based on the Bregman divergence.

Abstract: A torsional-vibration-reducing-device manufacturing method includes: molding an input rotating member and an output rotating member through punching press machining and bending press machining performed on plate materials; performing heat treatment on the molded input rotating member and the molded output rotating member; and assembling a damper product that includes, as components, the input rotating member and the output rotating member on which heat treatment has been performed, and a coil spring. The molding includes drilling processing for forming a hole opened in an outer-diameter direction with respect to the center line of rotation, at a position of at least one rotating member of the input rotating member and the output rotating member, the position serving as a spring holding section for holding the coil spring. The method further include cleaning the damper product with a cleaning solution and removing the cleaning solution remaining after the cleaning.

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: 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: 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 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, a computer program product, and a computer system for using a time-window based attention long short-term memory (TW-LSTM) network to analyze sequential data with time irregularity. A computer splits elapsed time into a predetermined number of time windows. The computer calculates average values of previous cell states in respective ones of the time windows and sets the average values as aggregated cell states for the respective ones of the time windows. The computer generates attention weights for the respective ones of the time windows. The computer calculates a new previous cell state, based on the aggregated cell states and the attention weights for the respective ones of the time windows. The computer updates a current cell state, based on the new previous cell state.

Abstract: A method for implementing artificial intelligence agents to perform machine learning tasks using predictive analytics to leverage ensemble policies for maximizing long-term returns includes obtaining a set of inputs including a set of ensemble policies and a meta-policy parameter, selecting an action for execution within the system environment using a meta-policy function determined based in part on the set of ensemble policies and the meta-policy function parameter, causing the artificial intelligence agent to execute the selected action within the system environment, and updating the meta-policy function parameter based on the execution of the selected action.

Abstract: A computer-implemented method for producing a formulation based on a prior distribution of a number of ingredients used in the formulation includes grouping a set of energy functions based on a number of ingredients used in a formulation, generating a probability distribution using the set of energy functions, obtaining at least one sample of the formulation by sampling from the probability distribution based on a previous sample, and triggering fabrication of the formulation in accordance with the at least one sample.

Abstract: A method for selecting an action, includes reading, into a memory, a Partially Observed Markov Decision Process (POMDP) model, the POMDP model having top-k action IDs for each belief state, the top-k action IDs maximizing expected long-term cumulative rewards in each time-step, and k being an integer of two or more, in the execution-time process of the POMDP model, detecting a situation where an action identified by the best action ID among the top-k action IDs for a current belief state is unable to be selected due to a constraint, and selecting and executing an action identified by the second best action ID among the top-k action IDs for the current belief state in response to a detection of the situation. The top-k action IDs may be top-k alpha vectors, each of the top-k alpha vectors having an associated action, or identifiers of top-k actions associated with alpha vectors.

Abstract: A computer-implemented method for solving a MAX SAT instance in provided in which a MAX SAT instance is transformed into a MAX 3SAT instance. The MAX 3SAT instance is transformed into a MAX 2SAT instance which is solved for an optimum solution. A solution to the MAX SAT instance is recovered from the MAX 2SAT optimum solution.

Abstract: Methods and apparatus are provided for estimating anomalous sensors. The apparatus includes a target data acquiring section to acquire a plurality of sets of target data serving as an examination target, each set of target data being output by a plurality of sensors. The apparatus further includes a calculating section to calculate, for each of a plurality of sensor groups such that each sensor group includes at least two sensors among the plurality of sensors, a degree of difference of a target data distribution of the plurality of sets of target data relative to a reference data distribution of output from the sensor group. The apparatus additionally includes an estimating section to estimate one or more sensors among the plurality of sensors to be a source of outlierness, based on a calculation result of the calculating section.

Abstract: A method is provided for rule creation that includes receiving (i) a MDP model with a set of states, a set of actions, and a set of transition probabilities, (ii) a policy that corresponds to rules for a rule engine, and (iii) a set of candidate states that can be added to the set of states. The method includes transforming the MDP model to include a reward function using an inverse reinforcement learning process on the MDP model and on the policy. The method includes finding a state from the candidate states, and generating a refined MDP model with the reward function by updating the transition probabilities related to the state. The method includes obtaining an optimal policy for the refined MDP model with the reward function, based on the reward policy, the state, and the updated probabilities. The method includes updating the rule engine based on the optimal policy.

Abstract: Methods and systems for detecting seizures include generating two-dimensional frames that each include a first set of elements that store measurements from sensors and a second set of elements that store values calculated from said measurements. The two-dimensional frames are classified using a machine learning model. It is determined that a subject experienced a seizure during a measurement interval based on an output of the machine learning model. A corrective action is performed responsive to the determination that the subject experienced a seizure.

Abstract: A computer-implemented method is provided for generating a new formulation. The method includes dividing each of input formulations into constituent topics, based on analysis results for an analysis of the input formulations using a topic model algorithm. The method further incudes includes receiving an input query that specifies a set of fragrance. notes to he used to generate the new formulation, The method also includes choosing one of the input formulations which includes the set of fragrance notes to be used to generate the new formulation. The method additionally includes clustering the constituent topics of the chosen one of the input formulations based on a similarity metric. The method further includes generating the new formulation as a response to the input query by selecting, from the input formulations, materials for each of the clustered ones of the constituent topics.

Abstract: A method is provided for rule creation that includes receiving (i) a MDP model with a set of states, a set of actions, and a set of transition probabilities, (ii) a policy that corresponds to rules for a rule engine, and (iii) a set of candidate states that can be added to the set of states. The method includes transforming the MDP model to include a reward function using an inverse reinforcement learning process on the MDP model and on the policy. The method includes finding a state from the candidate states, and generating a refined MDP model with the reward function by updating the transition probabilities related to the state. The method includes obtaining an optimal policy for the refined MDP model with the reward function, based on the reward policy, the state, and the updated probabilities. The method includes updating the rule engine based on the optimal policy.

Abstract: A method is provided for determining graph isomorphism. The method includes initializing a hash value for each of a plurality of vertexes in a first labelled graph and a second labelled graph by assigning an integer value as the hash value, to form a first set of hash values for the vertexes in the first graph and a second set of hash values for the vertexes in the second graph. The integer value for a given vertex is assigned based on a label of the given vertex in the graphs. The method includes performing a determination of whether the first and second labelled graphs are isomorphic, by comparing the first and second sets of hash values. The method includes initiating a performance of an action that changes a state of a controlled object to another state, responsive to the determination. Each graph includes a mixture of hard and soft labels.

Abstract: A method is provided for determining graph isomorphism. The method includes initializing a hash value for each of a plurality of vertexes in a first labelled graph and a second labelled graph by assigning an integer value as the hash value, to form a first set of hash values for the vertexes in the first graph and a second set of hash values for the vertexes in the second graph. The integer value for a given vertex is assigned based on a label of the given vertex in the graphs. The method includes performing a determination of whether the first and second labelled graphs are isomorphic, by comparing the first and second sets of hash values. The method includes initiating a performance of an action that changes a state of a controlled object to another state, responsive to the determination. Each graph includes a mixture of hard and soft labels.

Abstract: Common data are maintained by a system including a plurality of node devices that each store a respective portion of a common data in a respective database, wherein a node device of the plurality of node devices stores a first portion of the common data, and receives a hash value of a second portion of the common data that is different from the first portion, in response to an update of the second portion of the common data.