Abstract: A processor-implemented method including, based on a first shape of a first tensor and a second shape of a second tensor used in an operation with the first tensor, determining a broadcasting type related to an extension of the first shape and the second shape, determining respective first shape offsets for each dimension of the first shape and respective second shape offsets for each dimension of the second shape based on the broadcasting type, determining respective first tensor offsets for each dimension of the first tensor and respective second tensor offsets for each dimension of the second tensor based on the broadcasting type, the respective first shape offsets for each dimension of the first shape, and the respective second shape offsets for each dimension of the second shape, determining a first offset of a first element included in the first tensor and a second offset of a second element included in the second tensor based on the respective first tensor offsets and the respective second tensor offse

Abstract: A method with biometric information spoof detection includes extracting an embedding vector from an intermediate layer of a neural network configured to detect whether biometric information of a user is spoofed from an image including the biometric information; detecting first information regarding whether the biometric information is spoofed, based on the embedding vector; and detecting second information regarding whether the biometric information is spoofed based on whether the first information is detected, using an output vector output from an output layer of the neural network.

Abstract: A method performed by one or more processors includes: iteratively training layer-specific quantization levels and layer-specific quantization intervals of respective layers of a neural network of original weights by, for each training iteration, adjusting the quantization levels and quantization intervals to reduce a loss that is determined based on the original weights and is determined based on the original weights as quantized according to the quantization levels and quantization intervals at a current iteration of the training.

Abstract: The present invention relates to a hat having a rear-view camera that includes a hat body with an insertion body and a brim, an upward/downward extension and contraction part disposed on the peak of the insertion body and thus extending upward or contracting downward vertically to freely adjust the rear-view camera disposed on top thereof upward and downward in height, and a forward/backward extension and contraction part freely adjusted forward and backward in length from the top of the brim to freely adjust a display part forward and backward, so that the rear-view camera is freely adjusted in height on the top of the insertion body of the hat body to allow a video providing a situation behind a wearer who wears the hat body to be transmitted to the display part.

Abstract: A method of searching for hyperparameters for neural network learning includes: obtaining a preset early stop point; determining whether a current trial, among trials for searching for different combinations of hyperparameters, corresponds to a dry run trial; in response to a determination that the current trial corresponds to a dry run trial: executing learning epochs belonging to the current trial; searching for a combination of hyperparameters assigned to the current trial according to a result of the executing of the learning epochs; and changing the early stop point by based on whether an early stop with respect to a found combination of the hyperparameters is a success in each of the learning epochs.

Abstract: The present invention relates to a mobile hearing aid having foldable earphones and howling prevention circuits mounted on headwear, including: a support member disposed on the inner periphery of the headwear and made of plastic or metal; and sensors provided on the surfaces of the earphones facingly covering a wearer's ears to detect the infrared radiation emitted from the human body, wherein hearing aid sounds are provided to the wearer when the earphones are covered on his or her ears and muted when the earphones are open from his or her ears, thereby preventing the occurrence of howling from the earphones open from his or her ears.

Abstract: A method of a system including a processor including recording experiment information of a job in connection with job information generated based on an execution of a job of a computer cluster system, and controlling further execution of a job, by the computer cluster system, by transmitting a change in the experiment information to the computer cluster system based on the job information.

Abstract: A method and apparatus that detects whether biometric information is spoofed is provided. The method receives, from a sensor, first feature information including a static feature associated with biometric information of a user, and a dynamic feature obtained based on images related to the biometric information, detects whether the biometric information is spoofed based on a first score calculated based on the first feature information, fuses the first score with a second score calculated based on second feature information extracted from the images, based on a result of the detecting that the biometric information is spoofed based on the first score, and detects that the biometric information is spoofed based on a fused score.

Abstract: The present invention relates to a mobile hearing aid having foldable earphones and howling prevention circuits mounted on headwear, including: a support member disposed on the inner periphery of the headwear and made of plastic or metal; and sensors provided on the surfaces of the earphones facingly covering a wearer's ears to detect the infrared radiation emitted from the human body, wherein hearing aid sounds are provided to the wearer when the earphones are covered on his or her ears and muted when the earphones are open from his or her ears, thereby preventing the occurrence of howling from the earphones open from his or her ears.

Abstract: The present invention relates to a hat having a rear-view camera that includes a hat body with an insertion body and a brim, an upward/downward extension and contraction part disposed on the peak of the insertion body and thus extending upward or contracting downward vertically to freely adjust the rear-view camera disposed on top thereof upward and downward in height, and a forward/backward extension and contraction part freely adjusted forward and backward in length from the top of the brim to freely adjust a display part forward and backward, so that the rear-view camera is freely adjusted in height on the top of the insertion body of the hat body to allow a video providing a situation behind a wearer who wears the hat body to be transmitted to the display part.

Abstract: A speaker recognition method and apparatus receives a first voice signal of a speaker, generates a second voice signal by enhancing the first voice signal through speech enhancement, generates a multi-channel voice signal by associating the first voice signal with the second voice signal, and recognizes the speaker based on the multi-channel voice signal.

Abstract: A processor-implemented method includes: obtaining an input embedding vector corresponding to an input fingerprint image for authentication; determining a confidence value of the input embedding vector based on fingerprint data of an initial model including either one or both of a trained real fingerprint determination model and a trained fake fingerprint determination model that are provided in advance; and updating the initial model based on the input embedding vector, in response to the confidence value being greater than or equal to a first threshold.

Abstract: A speaker recognition method and apparatus receives a first voice signal of a speaker, generates a second voice signal by enhancing the first voice signal through speech enhancement, generates a multi-channel voice signal by associating the first voice signal with the second voice signal, and recognizes the speaker based on the multi-channel voice signal.

Abstract: A method with biometric information spoof detection includes extracting an embedding vector from an intermediate layer of a neural network configured to detect whether biometric information of a user is spoofed from an image including the biometric information; detecting first information regarding whether the biometric information is spoofed, based on the embedding vector; and detecting second information regarding whether the biometric information is spoofed based on whether the first information is detected, using an output vector output from an output layer of the neural network.

Abstract: A method and apparatus that detects whether biometric information is spoofed is provided. The method receives, from a sensor, first feature information including a static feature associated with biometric information of a user, and a dynamic feature obtained based on images related to the biometric information, detects whether the biometric information is spoofed based on a first score calculated based on the first feature information, fuses the first score with a second score calculated based on second feature information extracted from the images, based on a result of the detecting that the biometric information is spoofed based on the first score, and detects that the biometric information is spoofed based on a fused score.

Abstract: A speaker recognition method and apparatus receives a first voice signal of a speaker, generates a second voice signal by enhancing the first voice signal through speech enhancement, generates a multi-channel voice signal by associating the first voice signal with the second voice signal, and recognizes the speaker based on the multi-channel voice signal.

Abstract: A processor-implemented method includes: obtaining an input embedding vector corresponding to an input fingerprint image for authentication; determining a confidence value of the input embedding vector based on fingerprint data of an initial model including either one or both of a trained real fingerprint determination model and a trained fake fingerprint determination model that are provided in advance; and updating the initial model based on the input embedding vector, in response to the confidence value being greater than or equal to a first threshold.

Abstract: A speaker recognition method and apparatus receives a first voice signal of a speaker, generates a second voice signal by enhancing the first voice signal through speech enhancement, generates a multi-channel voice signal by associating the first voice signal with the second voice signal, and recognizes the speaker based on the multi-channel voice signal.

Abstract: In one aspect, method is provided for controlling a display device, comprising: displaying, on a touchscreen display, a first window executing a first application and a second window executing a second application; receiving, at the touchscreen display, a first command input to the first window and a second command input to the second window; determining whether the first command and the second command are received simultaneously; dispatching, by a processor, the first command; and dispatching, by the processor, the second command.

Abstract: In one aspect, method is provided for controlling a display device, comprising: displaying, on a touchscreen display, a first window executing a first application and a second window executing a second application; receiving, at the touchscreen display, a first command input to the first window and a second command input to the second window; determining whether the first command and the second command are received simultaneously; dispatching, by a processor, the first command; and dispatching, by the processor, the second command.