Abstract: A learning apparatus comprises one or more hardware processors, and one or more memories storing one or more programs configured to be executed by the one or more hardware processors, the one or more programs including instructions for, performing learning of a second learning model having an arrangement that is at least partially the same as an arrangement of a first learning model by distillation learning using an output of the first learning model, and dynamically changing, during the learning of the second learning model, at least one of a parameter of the first learning model, the arrangement of the first learning model, a parameter of the second learning model, and the arrangement of the second learning model.

Abstract: An information processing apparatus comprises a generating unit configured to generate supervised data relating to a topological invariant based on a topological property relating to supervised data corresponding to input data, and a training unit configured to perform, based on a geometric property relating to an output from a classifier to which the input data is input and the supervised data generated by the generating unit, training of the classifier.

Abstract: An information processing apparatus which executes a search for an architecture of a network model includes a first learning unit configured to execute learning of an architecture coefficient, a second learning unit configured to execute learning of a weight coefficient, and a control unit configured to execute control to advance the search by causing the first learning unit and the second learning unit to execute learning alternately. The control unit executes control to cause at least any one of the first learning unit and the second learning unit to execute learning on a network model including an architecture coefficient and a weight coefficient acquired at the current point in time using an output value output from a network model set as a teacher model which is configured based on an architecture coefficient and a weight coefficient acquired prior to the current point in time.

Abstract: An information processing apparatus configured to optimize an architecture of a network model includes at least one memory storing instructions, and at least one processor that, upon execution of the instructions, is configured to perform a search for the architecture based on data for learning, evaluate a topology of the network model that corresponds to the architecture obtained in a process of the search, and perform control to output a change in an evaluation result of the topology as the search progresses.

Abstract: An information processing apparatus comprises a generating unit configured to generate supervised data relating to a topological invariant based on a topological property relating to supervised data corresponding to input data, and a training unit configured to perform, based on a geometric property relating to an output from a classifier to which the input data is input and the supervised data generated by the generating unit, training of the classifier.

Abstract: The present invention provides a method for classifying biological tissues with high precision compared to a conventional method. When measuring a spectrum which has a two-dimensional distribution that is correlated with a slice of a biological tissue, and acquiring a biological tissue image from the two-dimensional measured spectrum, the method includes dividing an image region into a plurality of small blocks, and then reconstructing the biological tissue image by using the measured spectrum and a classifier corresponding to each of the regions.

Abstract: The present invention provides a method for classifying biological tissues with high precision compared to a conventional method. When measuring a spectrum which has a two-dimensional distribution that is correlated with a slice of a biological tissue, and acquiring a biological tissue image from the two-dimensional measured spectrum, the method includes dividing an image region into a plurality of small blocks, and then reconstructing the biological tissue image by using the measured spectrum and a classifier corresponding to each of the regions.

Abstract: A data processing apparatus that processes a spectral data item which stores, for each of a plurality of spectral components, an intensity value, includes a spectral component selecting unit and a classifier generating unit. The spectral component selecting unit is configured to select, based on a Mahalanobis distance between groups each composed of a plurality of spectral data items or a spectral shape difference between groups each composed of a plurality of spectral data items, a plurality of machine-learning spectral components from among the plurality of spectral components of the plurality of spectral data items. The classifier generating unit is configured to perform machine learning by using the plurality of machine-learning spectral components selected by the spectral component selecting unit and generate a classifier that classifies a spectral data item.

Abstract: The present invention provides a method for classifying biological tissues with high precision compared to a conventional method. When measuring a spectrum which has a two-dimensional distribution that is correlated with a slice of a biological tissue, and acquiring a biological tissue image from the two-dimensional measured spectrum, the method includes dividing an image region into a plurality of small blocks, and then reconstructing the biological tissue image by using the measured spectrum and a classifier corresponding to each of the regions.

Abstract: High-speed data processing is achieved by measuring spectral data using a multivariate analysis. This is accomplished by a determining sampling intervals or sampling data to be used in the multivariate analysis, obtaining a spectral data group of the determined sampling intervals, and carrying out the multivariate analysis using the obtained spectral data group.

Abstract: A subject information obtaining apparatus has: a light source; a plurality of receiving elements which receive acoustic waves generated from a subject, and output signals; a memory unit for storing, for each of a plurality of predetermined positions, information to represent signals which are output from the plurality of receiving elements when an acoustic wave source is assumed to exist in the position; and an estimating unit for estimating a distribution of acoustic wave sources. The estimating unit assumes a distribution of acoustic wave sources, obtains signals corresponding to positions of respective acoustic wave sources in the assumed distribution from the stored information, and defines a distribution of acoustic wave sources, of which degree of coincidence between the obtained signals and signals obtained in an actual measurement is highest, as the distribution of acoustic wave sources.

Abstract: Provided are a method of reconstructing a biological tissue image, and a method and apparatus for acquiring a biological tissue image, which allow a biological tissue to be identified with higher accuracy than ever before. The reconstruction of the biological tissue image is performed by measuring spectra having a two-dimensional distribution correlated with a biological tissue section, and acquiring a biological tissue image from the two-dimensional measured spectra through utilization of the measured spectra and an classifier.

Abstract: Noise reduction processing for measured spectrum data is performed without any information loss due to discrete data characteristics of the measured spectrum data. Optical spectra in one or more cross-sections are measured through use of a signal correlated with a substance distributed in a biological tissue, and a biological tissue image having reduced noise is reconstructed from the spectra.

Abstract: High-speed data processing is achieved by measuring spectral data using a multivariate analysis. This is accomplished by a determining sampling intervals or sampling data to be used in the multivariate analysis, obtaining a spectral data group of the determined sampling intervals, and carrying out the multivariate analysis using the obtained spectral data group.

Abstract: The present invention provides a method for classifying biological tissues with high precision compared to a conventional method. When measuring a spectrum which has a two-dimensional distribution that is correlated with a slice of a biological tissue, and acquiring a biological tissue image from the two-dimensional measured spectrum, the method includes dividing an image region into a plurality of small blocks, and then reconstructing the biological tissue image by using the measured spectrum and a classifier corresponding to each of the regions.

Abstract: A more effective noise reduction method is provided. In the method, when mass spectrum information having a spatial distribution is processed, the whole data is taken as three-dimensional data (positional information is stored in an xy plane, and spectral information is stored along a z-axis direction), and three-dimensional wavelet noise reduction is performed by applying preferable basis functions to a spectral direction and a peak distribution direction (in-plane direction).

Abstract: To provide a method that reduces an influence of dependence of an ionizing beam in an incident direction or uneven irradiation to a sample on a result of mass spectrometry, and can measure mass distribution with high reliability. A mass distribution measuring method according to the present invention includes: changing a direction of irradiating the ionizing beam to a sample surface; acquiring a plurality of mass distribution images in a plurality of incident directions; performing image transform of the mass distribution images according to an angle formed by an incident direction of the ionizing beam and a substrate surface; synthesizing the plurality of transformed images; and outputting the synthesized mass distribution images.

Abstract: When correcting the acoustic wave refraction occurring on the interface between mediums having different sound speeds by Snell's law, an applicable back-projection method is limited to a time domain method. An image data generating method performed to receive and convert an acoustic wave generated by irradiating a subject with light into a first electrical signal with an acoustic wave receiver via a medium having a sound speed different from that of the subject, and to generate image data based on the first electrical signal is provided, wherein a second electrical signal obtained when the acoustic wave is received at each virtual reception point is generated based on the first electrical signal through an integral calculation performed by using an advanced Green's function, and image data is generated based on the second electrical signal.

Abstract: A more effective noise reduction method is provided. In the method, when mass spectrum information having a spatial distribution is processed, the whole data is taken as three-dimensional data (positional information is stored in an xy plane, and spectral information is stored along a z-axis direction), and three-dimensional wavelet noise reduction is performed by applying preferable basis functions to a spectral direction and a peak distribution direction (in-plane direction).

Abstract: When correcting the acoustic wave refraction occurring on the interface between mediums having different sound speeds by Snell's law, an applicable back-projection method is limited to a time domain method. An image data generating method performed to receive and convert an acoustic wave generated by irradiating a subject with light into a first electrical signal with an acoustic wave receiver via a medium having a sound speed different from that of the subject, and to generate image data based on the first electrical signal is provided, wherein a second electrical signal obtained when the acoustic wave is received at each virtual reception point is generated based on the first electrical signal through an integral calculation performed by using an advanced Green's function, and image data is generated based on the second electrical signal.