Abstract: A signal processing device includes an approximate curved surface conversion unit that includes a first stacked autoencoder pretrained on the basis of learning input data constituted by coordinate data acquired for each of multiple elements of an object, and that obtains approximate curved surface data indicating an approximate curved surface of the object in an intermediate layer of the first stacked autoencoder, on the basis of input data constituted by the coordinate data acquired for each of the elements, and a geometric modulation processing unit that includes a second stacked autoencoder having learned by machine learning on the basis of learning input data constituted by the approximate curved surface data and on the basis of training data constituted by a result obtained by coordinate conversion for each of the elements in a geometric modulation process performed for the object, and performs the geometric modulation process.

Abstract: A signal processing device according to the present technology includes a stacked auto encoder that processes an input signal from a sensor, a control line associated learner including a neural network and subjected to control line associated learning for performing learning by associating different event aspects related to a specific event with values of different control lines with a feature quantity obtained in an intermediate layer of the stacked auto encoder after pretraining as an input, and a refactorer that obtains a difference between a first output that is an output of the control line associated learner when a first value is given to the control line, and a second output that is an output of the control line associated learner when a second value different from the first value is given to the control line.

Abstract: A signal processing device includes an approximate curved surface conversion unit that includes a first stacked autoencoder pretrained on the basis of learning input data constituted by coordinate data acquired for each of multiple elements of an object, and that obtains approximate curved surface data indicating an approximate curved surface of the object in an intermediate layer of the first stacked autoencoder, on the basis of input data constituted by the coordinate data acquired for each of the elements, and a geometric modulation processing unit that includes a second stacked autoencoder having learned by machine learning on the basis of learning input data constituted by the approximate curved surface data and on the basis of training data constituted by a result obtained by coordinate conversion for each of the elements in a geometric modulation process performed for the object, and performs the geometric modulation process.

Abstract: A signal processing device according to the present technology includes a feature quantity extraction unit including a neural network and trained to extract a feature quantity for a specific event with respect to an input signal from a sensor. and a correction unit that performs correction of the input signal on the basis of the feature quantity extracted by the feature quantity extraction unit.

Abstract: A signal processing device according to the present technology includes a stacked auto encoder that processes an input signal from a sensor, a control line associated learner including a neural network and subjected to control line associated learning for performing learning by associating different event aspects related to a specific event with values of different control lines with a feature quantity obtained in an intermediate layer of the stacked auto encoder after pretraining as an input, and a refactorer that obtains a difference between a first output that is an output of the control line associated learner when a first value is given to the control line, and a second output that is an output of the control line associated learner when a second value different from the first value is given to the control line.

Abstract: A signal processing apparatus includes: a data input unit to which image data is input; an output unit configured to output an output value based on the data input to the data input unit; an expectation feedback calculator configured to calculate a difference between an expectation based on the input data and the output value; and a Bayesian estimator to which information on the difference and information based on the image data are input and which is configured to perform machine learning in order to approximate the output value to the expectation based on the input information and to search for an optimum configuration.