Sony Corporation

Riken Corporation

Jun Tani

Masato Ito

Kuniaki Noda

Yukiko Yoshiike

Ryunosuke Nishimoto

An information processing apparatus, includes a lower time series data generation unit having a plurality of recurrent neural networks which learn predetermined time series data, and generating prediction time series data. An upper time series data generation unit has recurrent neural networks which learn error time series data that is time series data of errors raised at the time of the learning by the respective plural recurrent neural networks of the lower time series data generation unit. Generation of prediction error time series data that is time series data of prediction errors; and a conversion unit that performs nonlinear conversion for the prediction errors generated by the upper time series data generation unit. The lower time series data generation unit outputs the prediction time series data according to the prediction errors.

Information processing apparatus, method, and program using recurrent neural networks

An information processing apparatus including a learning unit that learns a predetermined time-series pattern. An output unit outputs a time-series pattern corresponding to the result of learning by the learning unit. An adjusting unit supplied with a time-series pattern obtained from an action by an action unit on the basis of a time-series pattern supplied from the output unit and external teaching for the action adjusts a time-series pattern supplied from the output unit correspondingly to the input time-series pattern. The learning unit learns the time-series pattern supplied from the output unit and adjusted by the adjusting unit.

Information processing apparatus and method, and program for teaching an action to a device in a time-series pattern

An information processing method and an information processing apparatus in which the learning efficiency may be improved and the scale may be extended readily. An integrated moduleis formed by a movement pattern learning module by a local expression scheme. The local modules-to-of the integrated moduleare each formed by a recurrent neural network as a movement pattern learning model by a distributed expression scheme. The local modules-to-are caused to learn plural movement patterns. Outputs from the local modules-to-, supplied with preset parameters, as inputs, are multiplied by gates-to-with coefficients Wto W, respectively, and the resulting products are summed together and output.

Information processing apparatus and method, program storage medium and program

This invention relates to an information processing device and method that enable generation of an unlearned new pattern. Data xcorresponding to a predetermined time series pattern is inputted to an input layer () of a recurrent neural network (), and a prediction value x*is acquired from an output layer. A difference between teacher data xand the prediction value x*is learned by a back propagation method, and a weighting coefficient of an intermediate layeris set at a predetermined value. After the recurrent neural network is caused to learn plural time series patterns, a parameter having a different value from the value in learning is inputted to parametric bias nodes (-), and an unlearned time series pattern corresponding to the parameter is generated from the output layer (). This invention can be applied to a robot.

Information processing apparatus and method

An information processing apparatus includes a first recurrent neural network (RNN) for performing processing which corresponds to a time-series and a second RNN for processing another correlated time-series. The difference between a context set output by the first RNN and a context set output by the second RNN is computed by a subtractor, and the obtained difference is used as a prediction error. Backpropagation is performed based on the prediction error, thus determining a coefficient for each neuron of an output layer, an intermediate layer, and an input layer.

Information processing apparatus and method, and recording medium

This invention provides a data processing apparatus which can store and recall more complicated time-series data than those processed in related art technologies. In the data processing apparatus, a recurrent neural network (RNN) of higher layer generates long-period parameter and supplies it to an input layer of RNN of lower layer via a computing block. The RNN uses this input as a parameter and computes short-period input.

Data processing apparatus and method, recording medium, and program

A learning-type movement control apparatus that learns the movement of an operation control device, predicts the movement thereof, and drives it so as to automatically move. The apparatus comprises an operation control device having a predetermined portion that is displaced according to a force exerted in an arbitrary direction, outputs the amount of the displacement at least as one-dimensional position-representing information, receives a feedback signal carrying information generated by adding displacement information to the position-representing information, and drives the predetermined portion according to a direction and a displacement that are based on the feedback signal. The apparatus also includes a learning section that receives the position-representing information and performs learning of the movement of the operation control device. The apparatus further includes a predicting section that performs prediction of a displacement of the operation control device according to the position-representing information the learning result of the learning section, and generates the feedback signal by adding the displacement information to the position-representing information.

Learning-type movement control apparatus, method therefor, and distribution medium therefor

A land mark recognition apparatus presenting an enhanced learning capability with its neural net. Color image data of a land mark picked up by a television camera is quantized in the space defined by hue and chroma. Specifically, the color image data defined by hue and chroma falls within an area A1, the data is quantized as red data. Similarly, color image data falls within areas A3 and A3, the data is quantized as green and blue data, respectively. The color image data, after being quantized into a small number of data, is stored in the neural net.

Land mark recognition method for mobile robot navigation

A signal processing method for efficiently searching an optimum solution in a neural network by including a term of a nonlinear resistance in an equation of motion and changing such nonlinear resistance periodically. According to the method, the range of absolute values of connection weights between units in the neural network is limited by the equation of motion, hence preventing a prolonged search time that may otherwise be caused by excessive extension of the search scope beyond the requisite. A plurality of patterns are previously embedded or stored in the neural network and, upon input of a predetermined key pattern, the nonlinear resistance is changed periodically to recall a pattern similar to the key pattern, whereby any desired pattern can be searched or retrieved with rapidity and facility out of the complicated patterns. A process of calculating the next position of an articulated robot corresponding to an optimum solution is repeated while periodically changing a nonlinear resistance included in another equation of the positional energy of the robot, thereby acquiring the data of the robot path up to a desired goal.

Method of processing signals within a neural network to position arobot

To enable the pattern matching between a shifted input pattern and the standard pattern, a plurality of standard patterns are stored in a standard pattern associative memory network 12. A pattern shifted relative to the standard pattern is inputted to the input pattern network 11 and a restriction condition of when the input pattern is shifted relative to the standard pattern is stored in a coordinate associated network 14. In an association network 13, weights and biases are determined so that the respective units of the network 13 are activated most intensely when the input pattern and the standard pattern match correctly each other in response to the signals from the respective networks 11, 12, and 14.

Growing community of inventors

Tokyo, Japan

Jun Tani