Abstract: A computer generates a formal planning domain description. The computer receives a first text-based description of a domain in an AI environment. The domain includes an action and an associated attribute, and the description is written in natural language. The computer receives the first text-based description of the domain and extracts a first set of domain actions and associated action attributes. The computer receives audio-visual elements depicting the domain, generates a second text-based description, and extracts a second set of domain actions and associated action attributes. The computer constructs finite state machines corresponding to the extracted actions and attributes. The computer converts the FSMs into a symbolic model, written in a formal planning language, that describes the domain.

Abstract: A computer-implemented method for estimating a state-action value function for a Fitted Q-iteration is provided including obtaining a set of tuples D and a discount factor ?, each of the set of tuples including a state s, an action a, a reward r, and a resulting state s?, constructing a zero-suppressed decision diagram (ZDD) of feature vectors {?(s?, a?)|a??(s?)} for each of the resulting states s? of the set of tuples, where the feature vector ?(s, a) is a sparse bit vector {0,1}D and (s?) is the set of actions applicable at state s?, updating parameters w?D, ? of a state-action value function Q (s, a; w, ?); and repeating the updating step a predetermined times by incrementing t.

Abstract: A method performs a Differentiable Point Process (DPP). Generate a first sample sk by sampling from a Poisson process with reference to an upper bound ? of a conditional intensity function representing the DPP given a first set of samples S. Determine whether sk>T, output a second set of samples and train a probabilistic model using when sk>T, and perform the next four steps (generate a second sample, add, add, update) and return to the first step (generate a first sample) when sk?T, where T denotes an observation length. Generate a second sample [ p k r k ] by sampling from a concrete distribution with reference to a parameter of the distribution defined by the conditional intensity function and a temperature ?, given a second set of samples . Add a pair of sk and pk to and discard rk. Add sk to S. Update k to k+1.

Abstract: Production rules that represent molecule structures are generated by generating a hypergraph from each of a plurality of molecule structures, performing a tree decomposition of each hypergraph to obtain a syntax tree corresponding to the hypergraph, and extracting a set of production rules for producing each hypergraph, by using connections of nodes in the corresponding tree decomposition.

Abstract: A computer-implemented method for implementing a computer system task involving streaming data by removing biased gradients from memory includes generating a parameter sequence including a plurality of parameters corresponding to respective iteration counts. Generating the parameter sequence includes obtaining a first parameter value corresponding to a given iteration count by updating memory corresponding to the given iteration count based on a second parameter value corresponding to a prior iteration count, adapting a size of the updated memory to remove biased gradients, and obtaining the first parameter value by performing a step of a gradient descent method based on the adaptation and the second parameter value. The method further includes learning a time-series model based on the parameter sequence, and implementing a computer system task using the time-series model.

Abstract: Techniques regarding generating and/or training one or more symbolic models are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a training component that can train a symbolic model via active machine learning. The symbolic model can characterize a formal planning language for a planning domain as a plurality of digital image sequences.

Abstract: In a method for selecting a model, a processor inputs a data stream with observable variables into a first model having a first number of states and a second model having a second number of states. A processor estimates first and second model parameters of the first model and the second model, respectively, using the observable variables. A processor estimates latent variables that associate each observable variable with one of the states. A processor calculates state-permutation-invariant differences between each time consecutive pair of latent variables. A processor calculates a first time inconsistency measure for the first model by summarizing first state-permutation-invariant differences, and calculates a second time inconsistency measure for the second model by summarizing second state-permutation-invariant differences. A processor selects a smallest time inconsistency measure between the first time inconsistency measure and the second time inconsistency measure.

Abstract: Computer-implemented methods, computer program products, and systems are provided for multi-step ahead forecasting. A method includes configuring, by a processor device, a Vector Autoregression (VAR) model to generate a multi-step-ahead forecast based on previous observations. The previous observations are predictors and the multi-step-ahead forecast is a response to the predictors. The method further includes training, by the processor device, the VAR model using complex-valued weight parameters to avoid a training result relating to any of a divergence and a convergence to zero.

Abstract: A system, method, and computer program product for computational molecular design are disclosed. The method includes receiving an input molecule, encoding the input molecule as a vector in latent space, identifying a target region in the latent pace, sampling latent vectors from the target region, and generating two or more discrete representations of molecules for each of the sampled latent vectors by decoding the sampled latent vectors via sequential decision-making, which includes selecting most likely symbols at each step. Further, the method includes outputting, for each sampled latent vector, a unique molecule selected from the discrete representations of molecules. The system includes at least one processing component, at least one memory component, an encoder, a sampling module, and a decoder, which are configured to carry out the method. The computer program product includes a computer readable storage medium having program instructions to cause a device to perform the method.

Abstract: A computer generates a formal planning domain description. The computer receives a first text-based description of a domain in an AI environment. The domain includes an action and an associated attribute, and the description is written in natural language. The computer receives the first text-based description of said domain and extracts a first set of domain actions and associated action attributes. The computer receives audio-visual elements depicting the domain, generates a second text-based description, and extracts a second set of domain actions and associated action attributes. The computer constructs finite state machines corresponding to the extracted actions and attributes. The computer converts the FSMs into a symbolic model, written in a formal planning language, that describes the domain.

Abstract: Embodiments for intelligent application scenario testing and error detection by a processor. One or more modified application scenarios may be automatically generated from an initial application scenario having configuration data and a plurality of operations relating to an error. The one or more modified application scenarios are variations of the initial application. The one or more modified application scenarios may be executed to detect the existence or non-existence of the error in the one or more modified application scenarios.

Abstract: A system and method for reaction rules database correction. The method includes receiving a user-input correction to a first reaction rule in a reaction rules database, and locating a second reaction rule in the reaction rules database that is similar to the first reaction rule. The method also includes calculating a correctness score for the second reaction rule, and determining that the correctness score for the second reaction rule is below a threshold correctness score. Additionally, the method includes presenting, in response to the determining that the correctness score for the second reaction rule is below the threshold correctness score, the second reaction rule to a user, receiving a user-input correction to the second reaction rule, and updating the reaction rules database to include the user-input correction to the second reaction rule.

Abstract: A computer-implemented method is provided for learning a model corresponding to a target function that changes in time series. The method includes acquiring a time-series parameter that is a time series of input parameters including parameter values expressing the target function. The method further includes propagating propagation values, which are obtained by weighting parameters values at time points before one time point according to passage of the time points, to nodes in the model associated with the parameter values at the one time point. The method also includes calculating a node value of each node using each propagation value propagated to each node. The method additionally includes updating a weight parameter used for calculating the propagation values propagated to each node, using a difference between the target function at the one time point and a prediction function obtained by making a prediction from the node values of the nodes.

Abstract: A vehicular boarding assistance device includes: a slope main body provided in a body of a vehicle so as to project and retract and configured to form a slope by being bridged between the body and a ground surface in a state of projecting from the body; a slope drive source configured to drive the slope main body so as to project and retract; a seat drive source configured to drive at least one of a plurality of seats installed on a floor of the vehicle; and a control unit configured to drive and control the slope drive source such that the slope main body projects and drive and control the seat drive source such that an occupying region of a boarding assistance target moving on the slope and moving to the floor is secured on the floor.

Abstract: A computer-implemented method for implementing a computer system task involving nonstationary streaming time-series data based on a bias-variance-based adaptive learning rate includes generating a parameter sequence including a plurality of parameters corresponding to respective iteration counts. Generating the parameter sequence includes obtaining a first parameter value corresponding to a given iteration count by calculating estimators of moments associated with an objective function corresponding to the given iteration count based on a second parameter value corresponding to a prior iteration count using a sequential mean tracking method, and obtaining the first parameter value by performing a step of a gradient descent method based on the calculated moments and the second parameter value. The method further includes learning a time-series model based on the parameter sequence, and implementing a computer system task using the time-series model.

Abstract: A computer-implemented method for implementing a computer system task involving streaming data by removing biased gradients from memory includes generating a parameter sequence including a plurality of parameters corresponding to respective iteration counts. Generating the parameter sequence includes obtaining a first parameter value corresponding to a given iteration count by updating memory corresponding to the given iteration count based on a second parameter value corresponding to a prior iteration count, adapting a size of the updated memory to remove biased gradients, and obtaining the first parameter value by performing a step of a gradient descent method based on the adaptation and the second parameter value. The method further includes learning a time-series model based on the parameter sequence, and implementing a computer system task using the time-series model.

Abstract: Computer-implemented methods, computer program products, and systems are provided for multi-step ahead forecasting. A method includes configuring, by a processor device, a Vector Autoregression (VAR) model to generate a multi-step-ahead forecast based on previous observations. The previous observations are predictors and the multi-step-ahead forecast is a response to the predictors. The method further includes training, by the processor device, the VAR model using complex-valued weight parameters to avoid a training result relating to any of a divergence and a convergence to zero.

Abstract: A computer-implemented method, a computer program product, and a computer processing system are provided for online learning for a Dynamic Boltzmann Machine (DyBM) with hidden units. The method includes imposing, by a processor device, limited connections in the DyBM where (i) a current observation x[t] depends only on latest hidden units h[t-1/2] and all previous observations xm and (ii) the latest hidden units h[t-1/2] depend on all the previous observations x[<t] while being independent of older hidden units h[t-1/2]. The method further includes computing, by the processor device, gradients of an objective function. The method also includes optimizing, by the processor device, the objective function in polynomial time using a stochastic Gradient Descent algorithm applied to the gradients.

Abstract: Production rules that represent molecule structures are generated by generating a hypergraph from each of a plurality of molecule structures, performing a tree decomposition of each hypergraph to obtain a syntax tree corresponding to the hypergraph, and extracting a set of production rules for producing each hypergraph, by using connections of nodes in the corresponding tree decomposition.

Abstract: A system and method for reaction rules database correction. The method includes receiving a user-input correction to a first reaction rule in a reaction rules database, and locating a second reaction rule in the reaction rules database that is similar to the first reaction rule. The method also includes calculating a correctness score for the second reaction rule, and determining that the correctness score for the second reaction rule is below a threshold correctness score. Additionally, the method includes presenting, in response to the determining that the correctness score for the second reaction rule is below the threshold correctness score, the second reaction rule to a user, receiving a user-input correction to the second reaction rule, and updating the reaction rules database to include the user-input correction to the second reaction rule.