Abstract: A light-emitting device including a solid-state light source that emits light having a peak wavelength in the range of 480 nm or less and a fluorescent film that covers the solid-state light source and includes at least one kind of phosphor, wherein the fluorescent film includes at least one kind of near-infrared phosphor that is excited by light from the solid-state light source, has a peak wavelength in the range exceeding 700 nm, and has an emission spectrum with a full width at half maximum of 100 nm or more in a range including the peak wavelength.

Abstract: A student neural network may be trained by a computer-implemented method, including: selecting a teacher neural network among a plurality of teacher neural networks, inputting an input data to the selected teacher neural network to obtain a soft label output generated by the selected teacher neural network, and training a student neural network with at least the input data and the soft label output from the selected teacher neural network.

Abstract: The present invention provides a reflective polarized-light separating diffraction-element usable in a wide wavelength region including an ultraviolet region, and an optical measurement device comprising the same. The reflective polarized-light separating diffraction-element comprises: a substrate (1); a reflection surface (2) formed on a surface of the substrate (1); and a lattice structured body assembly (3) that is provided on the reflection surface (2) and shows a form birefringence (?n*). The lattice structured body assembly (3) consists of lattice structured bodies (3A, 3B, 3C and 3D) of four patterns having lattice structures of different azimuths. The lattice structured bodies (3A, 3B, 3C and 3D) of a plurality of patterns are aligned on the reflection surface 2 in a predetermined direction such that the azimuths of the lattice structures change in a structurally periodic manner.

Abstract: Fusion of neural networks is performed by obtaining a first neural network and a second neural network. The first and the second neural networks are the result of a parent neural network subjected to different training. A similarity score is calculated of a first component of the first neural network and a corresponding second component of the second neural network. An interpolation weight is determined for the first and the second components by using the similarity score. A neural network parameter of the first component is updated based on the interpolation weight and a corresponding neural network parameter of the second component to obtain a fused neural network.

Abstract: Methods and systems for training a neural network include training language-specific teacher models using different respective source language datasets. A student model is trained, using the different respective source language datasets and soft labels generated by the language-specific teacher models, including shuffling the source language datasets and shuffling weights of language-dependent layers in language-specific parts of the student model. Weights of language-independent layers of the student model are copied to a language-independent layers of a target model to initialize language-independent layers of the target model. The target model is trained with a target language dataset.

Abstract: In a method for improving generation and relevancy of search results, a processor receives a search query comprising a search term. A processor generates a document group based on the search query and at least one synonym related to the search term in a synonym dictionary. The synonym dictionary may include search document attributes for base words and synonyms of the base words. A processor extracts, from the document group, an extracted document having a document attribute matching a search document attribute of the at least one synonym. A processor lists the extracted document as a search result.

Abstract: A method, computer system, and a computer program product for audio data augmentation are provided. Sets of audio data from different sources may be obtained. A respective normalization factor for at least two sources of the different sources may be calculated. The normalization factors from the at least two sources may be mixed to determine a mixed normalization factor. A first set of the sets may be normalized by using the mixed normalization factor and to obtain training data for training an acoustic model.

Abstract: A first user request which specifies a target document set wherein a first subset of the documents is flagged by a user. A primary flag table is created for the target document set. A first document subset is created matching the first user request. It is determined whether a number of flagged documents exceeds a first threshold. If so, a secondary flag table is created for the first document subset and flag data corresponding to the first document subset is stored in the secondary flag table. The flag data in the secondary flag table is merged into the primary flag table.

Abstract: A technique for constructing a model supporting a plurality of domains is disclosed. In the technique, a plurality of teacher models, each of which is specialized for different one of the plurality of the domains, is prepared. A plurality of training data collections, each of which is collected for different one of the plurality of the domains, is obtained. A plurality of soft label sets is generated by inputting each training data in the plurality of the training data collections into corresponding one of the plurality of the teacher models. A student model is trained using the plurality of the soft label sets.

Abstract: A technique for generating soft labels for training is disclosed. A teacher model having a teacher side class set is prepared. A collection of class pairs for respective data units is obtained. Class pairs includes classes labelled to corresponding data units from the teacher side class set and a student side class set different from the teacher side class set. A training input is fed into the teacher model to obtain a set of outputs for the teacher side class set. A set of soft labels for the student side class set is calculated from the set of the outputs by using at least an output obtained for a class within a subset of the teacher side class set having relevance to the member of the student side class set, based at least in part on observations in the collection of the class pairs.

Abstract: In a hydrogen production apparatus, a front end of a housing is closed by an opening/closing door. In a closed state of the opening/closing door, the upper end of the upper rod and the lower end of the lower rod in the opening/closing switching mechanism are disposed behind the first front frame piece and the second front frame piece of the housing, respectively. The axial distance between the upper end of the lower collar member and the second stopper is greater than the axial distance between the upper end of the upper collar member and the first stopper.

Abstract: An approach to identifying alternate soft labels for training a student model may be provided. A teaching model may generate a soft label for a labeled training data. The training data can be an acoustic file for speech or a spoken natural language. A pool of soft labels previously generated by teacher models can be searched at the label level to identify soft labels that are similar to the generated soft label. The similar soft labels can have similar length or sequence at the word phoneme, and/or state level. The identified similar soft labels can be used in conjunction with the generated soft label to train a student model.

Abstract: A method of training a student neural network is provided. The method includes feeding a data set including a plurality of input vectors into a teacher neural network to generate a plurality of output values, and converting two of the plurality of output values from the teacher neural network for two corresponding input vectors into two corresponding soft labels. The method further includes combining the two corresponding input vectors to form a synthesized data vector, and forming a masked soft label vector from the two corresponding soft labels. The method further includes feeding the synthesized data vector into the student neural network, using the masked soft label vector to determine an error for modifying weights of the student neural network, and modifying the weights of the student neural network.

Abstract: Methods and systems for training a neural network include clustering a full set of training data samples into specialized training clusters. Specialized teacher neural networks are trained using respective specialized training clusters of the specialized training clusters. Soft labels are generated for the full set of training data samples using the specialized teacher neural networks. A student model is trained using the full set of training data samples, the specialized training clusters, and the soft labels.

Abstract: Provided are (i) a solution for forming an organic semiconductor layer which solution has an excellent coating property, (ii) an organic semiconductor which is produced with use of the solution and which has high heat resistance, (iii) a layer which contains the organic semiconductor, and (iv) an organic thin film transistor which exhibits high electrical properties. A composition containing: an organic semiconductor; and a polymer (1) having at least one unit selected from the group consisting of units represented by formulae (1-a), (1-b), and (1-c). A composition containing the organic semiconductor, the polymer (1), and an organic solvent can be suitably used as a solution for forming an organic semiconductor layer.

Abstract: Some embodiments of the present invention are directed to techniques for training teacher neural networks (TNNs) and student neural networks (SNNs). A training data set is received with a lossless set of data and a corresponding lossy set of data. Two branches of a TNN are established, with one branch trained using the lossless data (a lossless branch) and one trained using the lossy data (a lossy branch). Weights for the two branches are tied together. The lossy branch, now isolated from the lossless branch, generates a set of soft targets for initializing an SNN. These generated soft targets benefit from the training of lossless branch through the weights that were tied together between each branch, despite isolating the lossless branch from the lossy branch during soft-target generation.

Abstract: A technique for data augmentation for speech data is disclosed. Original speech data including a sequence of feature frames is obtained. A partially prolonged copy of the original speech data is generated by inserting one or more new frames into the sequence of the feature frames. The partially prolonged copy is output as augmented speech data for training an acoustic model for training an acoustic model.

Abstract: A technique for detecting a signal tone in an audio signal is disclosed. A determination is made as to whether a peak modulation frequency in the audio signal is in a specific range or not to obtain a determination result. A measure regarding a modulation spectrum of the audio signal is calculated. The measure is calculated based on at least components of the modulation spectrum above a specific limit of modulation frequency. By using the determination result and the measure regarding the modulation spectrum, a judgement is done as to whether the audio signal contains a signal tone or not.

Abstract: A technique for training a neural network including an input layer, one or more hidden layers and an output layer, in which the trained neural network can be used to perform a task such as speech recognition. In the technique, a base of the neural network having at least a pre-trained hidden layer is prepared. A parameter set associated with one pre-trained hidden layer in the neural network is decomposed into a plurality of new parameter sets. The number of hidden layers in the neural network is increased by using the plurality of the new parameter sets. Pre-training for the neural network is performed.

Abstract: A light-emitting device including a solid-state light source that emits light having a peak wavelength in the range of 480 nm or less and a fluorescent film that covers the solid-state light source and includes at least one kind of phosphor, wherein the fluorescent film includes at least one kind of near-infrared phosphor that is excited by light from the solid-state light source, has a peak wavelength in the range exceeding 700 nm, and has an emission spectrum with a full width at half maximum of 100 nm or more in a range including the peak wavelength.