Abstract: An optical system affixed to an electronic apparatus is provided, including a first optical module, a second optical module, and a third optical module. The first optical module is configured to adjust the moving direction of a first light from a first moving direction to a second moving direction, wherein the first moving direction is not parallel to the second moving direction. The second optical module is configured to receive the first light moving in the second moving direction. The first light reaches the third optical module via the first optical module and the second optical module in sequence. The third optical module includes a first photoelectric converter configured to transform the first light into a first image signal.

Abstract: Provided is a neural-network-based classification method, including: generating, by a neural network, one or more score vectors corresponding to one or more samples respectively; determining a first subset of the one or more samples according to the one or more score vectors and a first decision threshold, wherein the first subset is associated with a first class; and selecting samples to be re-examined from the one or more samples according to the first subset.

Abstract: A training device and a training method for a neural network model. The training method includes: obtaining a data set; completing, according to the data set, a plurality of artificial intelligence (AI) model trainings to generate a plurality of models corresponding to the plurality of AI model trainings respectively; selecting, according to a first constraint, a first model set from the plurality of models; and selecting, according to a second constraint, the neural network model from the first model set.

Abstract: An electronic device and a method for training a neural network model are provided. The method includes: obtaining a first neural network model and a first pseudo-labeled data; inputting the first pseudo-labeled data into the first neural network model to obtain a second pseudo-labeled data; determining whether a second pseudo-label corresponding to the second pseudo-labeled data matching a first pseudo-label corresponding to the first pseudo-labeled data; in response to the second pseudo-label matching the first pseudo-label, adding the second pseudo-labeled data to a pseudo-labeled dataset; and training the first neural network model according to the pseudo-labeled dataset.

Abstract: A training device and a training method for a neural network model are provided. The training method includes: obtaining a data set; completing, according to the data set, a plurality of artificial intelligence (AI) model trainings to generate a plurality of models corresponding to the plurality of AI model trainings respectively; selecting, according to a first constraint, a first model set from the plurality of models; and selecting, according to a second constraint, the neural network model from the first model set.

Abstract: A fusion-based classifier, classification method, and classification system, wherein the classification method includes: generating a plurality of probability vectors according to input data, wherein each of the plurality of probability vectors includes a plurality of elements corresponding to a plurality of class respectively; selecting, from the plurality of probability vectors, a first probability vector having an extremum value corresponding to a first class-of-interest according to the first class-of-interest; and determining a class of the input data according to the first probability vector.

Abstract: A neural network-based classification method, including: obtaining a neural network and a first classifier; inputting input data to the neural network to generate a feature map; cropping the feature map to generate a first cropped part and a second cropped part of the feature map; inputting the first cropped part to the first classifier to generate a first probability vector; inputting the second cropped part to a second classifier to generate a second probability vector, wherein weights of the first classifier are shared with the second classifier; and performing a probability fusion on the first probability vector and the second probability vector to generate an estimated probability vector for determining a class of the input data.

Abstract: Provided is a neural-network-based classification method, including: generating, by a neural network, one or more score vectors corresponding to one or more samples respectively; determining a first subset of the one or more samples according to the one or more score vectors and a first decision threshold, wherein the first subset is associated with a first class; and selecting samples to be re-examined from the one or more samples according to the first subset.

Abstract: A fusion-based classifier, classification method, and classification system, wherein the classification method includes: generating a plurality of probability vectors according to input data, wherein each of the plurality of probability vectors includes a plurality of elements corresponding to a plurality of class respectively; selecting, from the plurality of probability vectors, a first probability vector having an extremum value corresponding to a first class-of-interest according to the first class-of-interest; and determining a class of the input data according to the first probability vector.

Abstract: A neural network-based classification method, including: obtaining a neural network and a first classifier; inputting input data to the neural network to generate a feature map; cropping the feature map to generate a first cropped part and a second cropped part of the feature map; inputting the first cropped part to the first classifier to generate a first probability vector; inputting the second cropped part to a second classifier to generate a second probability vector, wherein weights of the first classifier are shared with the second classifier; and performing a probability fusion on the first probability vector and the second probability vector to generate an estimated probability vector for determining a class of the input data.

Abstract: A deep neural network and a method for recognizing and classifying a multimedia data as one of a plurality of pre-determined data classes with enhanced recognition and classification accuracy and efficiency are provided. The use of the side branch(es) (or sub-side branch(es), sub-sub-side branch(es), and so on) extending from the main branch (or side branch(es), sub-side branch(es), and so on), the sequential decision making mechanism, and the collaborating (fusing) decision making mechanism in a deep neural network would equip a deep neural network with the capability for fast forward inference so as to enhance recognition and classification accuracy and efficiency of the deep neural network.

Abstract: A deep neural network and a method for recognizing and classifying a multimedia data as one of a plurality of pre-determined data classes with enhanced recognition and classification accuracy and efficiency are provided. The use of the side branch(es) (or sub-side branch(es), sub-sub-side branch(es), and so on) extending from the main branch (or side branch(es), sub-side branch(es), and so on), the sequential decision making mechanism, and the collaborating (fusing) decision making mechanism in a deep neural network would equip a deep neural network with the capability for fast forward inference so as to enhance recognition and classification accuracy and efficiency of the deep neural network.

Abstract: Systems and methods are disclosed for writing data to an optical disc. In one example, a method includes the steps of receiving data to be written to an optical disc, determining the size of the data to be written to the optical disc, generating a file system image for the optical disc, writing the file system image to the optical disc and writing the data to the optical disc at a space beginning at a LBA located at a distance equal to about the size of the data from the last available LBA and terminating at about the last available LBA of the optical disc.

Abstract: Systems and methods are disclosed for writing data to an optical disc. In one example, a method includes the steps of receiving data to be written to an optical disc, determining the size of the data to be written to the optical disc, generating a file system image for the optical disc, writing the file system image to the optical disc and writing the data to the optical disc at a space beginning at a LBA located at a distance equal to about the size of the data from the last available LBA and terminating at about the last available LBA of the optical disc.

Abstract: Digital data may be copied from a source device, or disc, to a target device, or disc, via an intermediary device, such as a hard drive. If the collective free storage space on all of the hard drive's partitions is sufficient to contain all of the contents of the source disc, a first portion of the content is saved on a plurality of the hard drive's partitions. The contents stored on the hard drive partitions are then written to a target disc and thereafter removed from or overwritten on the hard drive. Other portions of the source disc's contents may be saved to the hard drive in one or more partitions and then written to the target disc. This partial-copying of the source disc's contents may repeat until all of the source disc's files are copied to the target disc.

Abstract: A method for copying data onto a plurality of hard drive partitions first determines the total size of the source files, which may be on an optical disc or other device. The available space on one or more hard drive partitions is determined and totaled. If the total available storage space is greater than the total size of the source files, a first portion of the source files are stored on a first partition as one or more image files. The remaining portions of the source files are stored on one or more additional storage partitions as image files. After the files are copied to the storage partitions, a data file is established containing location information of each image file stored on the hard drive partitions. The stored image files on the hard drive partitions may then be sequentially or randomly written onto a target device, such as an optical disc.