Abstract: Provided is an information processing system for an autonomous system, the information processing system obtaining observation sensor data in the autonomous system and a target of the autonomous system, and including: an agent management unit that stores and manages an agent group; an attention unit configured to select an agent from the agent group based on the target; and an agent cooperation unit configured to generate a new agent in which inputs and outputs of selected agents are integrated and to train a generative model of the new agent based on the observation sensor data.

Abstract: A cooperative autonomous control is implemented in consideration of emotions of a person or another apparatus. An apparatus holds an internal model for predicting a future state of an environment, acquires observation data indicating a state of an environment observed by the apparatus, generates first state information using the observation data, generates second state information of an intelligent agent present around the apparatus based on the first state information, decides a self emotion of the apparatus based on the first state information, decides a self emotion of the intelligent agent based on the second state information, decides a social emotion based on self emotions of the apparatus and the intelligent agent, generates future first state information and future second state information using the internal model, and decides an action based on the future first state information, the future second state information, and the social emotion.

Abstract: An information processing apparatus and an information processing method capable of accurately recognizing an object to be sensed are provided. One or a plurality of learning models are selected from among learning models corresponding to a plurality of categories, a priority of each of the selected learning models is set, observation data obtained by sequentially compounding pieces of sensor data applied from a sensor is analyzed using the learning model and the priority of the learning model, a setting of sensing at a next cycle is selected based on an analysis result, predetermined control processing is executed in such a manner that the sensor performs sensing at the selected setting of sensing, and the learning model corresponding to the category estimated as the category to which a current object to be sensed belongs with a highest probability is selected based on the categories to each of which the previously recognized object to be sensed belongs.

Abstract: A robot system includes a robot controlled by a computer. The robot includes a control device and an observation device. The computer detects a plurality of objects in a periphery by using observation information obtained by observation of the observation device, stores first state information of each of the plurality of detected objects, predicts future states of the plurality of detected objects from the first state information by using a first model for predicting a future state of an object, generates second state information of the periphery obtained by observation of the plurality of detected objects, predicts a future state of the robot from the second state information by using the first model, and determines a future action of the robot based on a given action target, the predicted future states of the plurality of objects, and the predicted future state of the robot.

Abstract: To provide a robust information processing system against attacks by Adversarial Example. A neural network model 608, a latent space database 609 for storing position information in a latent space in which first output vectors, which are output vectors of a predetermined hidden layer included in the neural network model, are embedded concerning input data used for learning of the neural network model, and an inference control unit 606 for making an inference using the neural network model and the latent space database are provided. The inference control unit infers the input data based on the positional relationship between the second output vector, which is an output vector of the predetermined hidden layer concerning input data to be inferred, and the first output vectors in said latent space.

Abstract: To act appropriately in consideration of uncertainty of a surrounding environment, it is provided a control system for generating an action for controlling a controlled device, comprising: a reception module configured to receive sensor data acquired by observing a state of a surrounding environment of the controlled device; a self-recognition module configured to derive, through use of a self-recognition prediction model that predicts a self-range being a range having a predictability and a controllability relating to the controlled device, a self-recognition block that defines the self-range from the sensor data; a target action prediction module configured to derive, through use of a target action prediction model that predicts a target action of the controlled device, the target action from the sensor data; and a switching module configured to select one of the self-recognition block or the target action in order to generate an action of the controlled device.

Abstract: To generate a prediction image in which an outline of an object is clear and existence of the object is easily recognized, the image prediction system that generates a future prediction image and includes a gaze unit, a working memory unit, a control unit, and a generation model unit. The gaze unit controls a region including an object included in an observation image as a first gaze region. The working memory unit controls the first gaze region as a second gaze region when a difference in the first gaze region between the observation image and a prediction image is equal to or less than a predetermined value. The generation model unit generates prediction images of the first gaze region and the second gaze region. The control unit integrates the prediction image of the first gaze region and the prediction image of the second gaze region to generate a prediction image.

Abstract: An information processing apparatus and an information processing method capable of accurately recognizing an object to be sensed are provided. One or a plurality of learning models are selected from among learning models corresponding to a plurality of categories, a priority of each of the selected learning models is set, observation data obtained by sequentially compounding pieces of sensor data applied from a sensor is analyzed using the learning model and the priority of the learning model, a setting of sensing at a next cycle is selected based on an analysis result, predetermined control processing is executed in such a manner that the sensor performs sensing at the selected setting of sensing, and the learning model corresponding to the category estimated as the category to which a current object to be sensed belongs with a highest probability is selected based on the categories to each of which the previously recognized object to be sensed belongs.

Abstract: To generate a prediction image in which an outline of an object is clear and existence of the object is easily recognized, the image prediction system that generates a future prediction image and includes a gaze unit, a working memory unit, a control unit, and a generation model unit. The gaze unit controls a region including an object included in an observation image as a first gaze region. The working memory unit controls the first gaze region as a second gaze region when a difference in the first gaze region between the observation image and a prediction image is equal to or less than a predetermined value. The generation model unit generates prediction images of the first gaze region and the second gaze region. The control unit integrates the prediction image of the first gaze region and the prediction image of the second gaze region to generate a prediction image.

Abstract: A genetic algorithm controller that controls respective processes using a genetic algorithm is configured. The processes include generation of a crystal structure of an inorganic material, a mutation operation of a crystal structure, a crossing-over operation of a crystal structure, structural relaxation calculation of a crystal structure, calculation of a predictive value of an objective function, selection and weeding out of a crystal structure based on a predictive value of an objective function, observation of an objective function value of a crystal structure by first-principle calculation, update of a regression model based on a result of observing the objective function value, and end determination for a material generation process.

Abstract: To provide a robust information processing system against attacks by Adversarial Example. A neural network model 608, a latent space database 609 for storing position information in a latent space in which first output vectors, which are output vectors of a predetermined hidden layer included in the neural network model, are embedded concerning input data used for learning of the neural network model, and an inference control unit 606 for making an inference using the neural network model and the latent space database are provided. The inference control unit infers the input data based on the positional relationship between the second output vector, which is an output vector of the predetermined hidden layer concerning input data to be inferred, and the first output vectors in said latent space.

Abstract: An automatic program generation system that includes: an input unit that receives inputs of input data, target data, and design requirements for a first program to be generated; a program storage unit that stores a plurality of existing second programs; a program generation device that generates the first program; and an output unit that outputs the first program. The program generation device includes a program analysis unit that analyzes the plurality of second programs to generate a program model, a basic node/constraint generation unit that generates basic nodes and constraints for evolutionary computation based on the generated program model and the design requirements input from the input unit, and an optimization unit that generates the first program by the evolutionary computation based on the basic nodes and the constraints and the input data and the target data input from the input unit.

Abstract: An information processing system includes a learning model unit, a trainer unit for allowing the learning model unit to learn, and a storage unit. The storage unit stores a validation rule defined in advance that indicates a condition determining that an output value of the learning model unit for an input value is true. The trainer unit inputs a plurality of input values to the learning model unit, obtains a plurality of output values of the learning model unit for the plurality of input values, determines whether each of the output values is true for each of the input values by referring to the validation rule, and stores a pair of an output data, which is determined to be true in the plurality of output values, and the corresponding input value into the storage unit, as new training data for supervised learning.

Abstract: There is provided a system that forecasts an index value of a predetermined day based on input data of the predetermined day in which result data of an index value of a day before the predetermined day is stored, similarity between the input data of the predetermined day and each of the stored result data is calculated, a weight is calculated for each result data based on the calculated similarity, and a forecasted index value of the predetermined day is prepared based on the calculated weight, the result data, and the input data of the predetermined day.

Abstract: There is provided an automatic program generation system that includes: an input unit that receives inputs of input data, target data, and design requirements for a first program to be generated; a program storage unit that stores a plurality of existing second programs; a program generation device that generates the first program; and an output unit that outputs the first program generated by the program generation device, in which the program generation device includes a program analysis unit that analyzes the plurality of second programs stored in the program storage unit to generate a program model, a basic node/constraint generation unit that generates basic nodes and constraints for evolutionary computation based on the program model generated by the program analysis unit and the design requirements input from the input unit, and an optimization unit that generates the first program by the evolutionary computation based on the basic nodes and the constraints generated by the basic node/constraint genera

Abstract: A genetic algorithm controller that controls respective processes using a genetic algorithm is configured. The processes include generation of a crystal structure of an inorganic material, a mutation operation of a crystal structure, a crossing-over operation of a crystal structure, structural relaxation calculation of a crystal structure, calculation of a predictive value of an objective function, selection and weeding out of a crystal structure based on a predictive value of an objective function, observation of an objective function value of a crystal structure by first-principle calculation, update of a regression model based on a result of observing the objective function value, and end determination for a material generation process.

Abstract: A clock driver circuit comprises a first and a second clock driver 15a and 15b. In each of these clock drivers, a plurality of main drivers 19(1) through 19(n) have their input nodes and output nodes connected respectively to a first and a second common line 18 and 21. The second common line 21 is connected to a plurality of clock signal supply lines 20(1) through 20(m) which in turn are connected to the clock input nodes of second macro cells 16 each requiring a clock signal. In a test mode, the first and second common lines 18a and 21a of the first clock driver 15a and the first and second common lines 18b and 21b of the second clock driver 15b are electrically connected by first and second connection means 22 and 24, respectively. Thus, a clock driver circuit is provided that offers high driving ability with negligible clock skews in both normal mode and test mode.