Abstract: An artificial neural network (ANN) quantization method for generating an output ANN by quantizing an input ANN includes: obtaining second parameters by quantizing first parameters of the input ANN; obtaining a sample distribution from an intermediate ANN in which the obtained second parameters have been applied to the input ANN; and obtaining a fractional length for the sample distribution by quantizing the obtained sample distribution.

Abstract: A method and apparatus for generating a fixed point neural network are provided. The method includes selecting at least one layer of a neural network as an object layer, wherein the neural network includes a plurality of layers, each of the plurality of layers corresponding to a respective one of plurality of quantization parameters; forming a candidate parameter set including candidate parameter values with respect to a quantization parameter of the plurality of quantization parameters corresponding to the object layer; determining an update parameter value from among the candidate parameter values based on levels of network performance of the neural network, wherein each of the levels of network performance correspond to a respective one of the candidate parameter values; and updating the quantization parameter with respect to the object layer based on the update parameter value.

Abstract: An operation method of a computing device includes selecting first data on which a first pruning is to be performed, down-scaling a first plurality of weights included in a first output channel associated with the first data, up-scaling a second plurality of weights used to generate second data to be multiplied by a weight having a major value from among the first plurality of weights included in the first output channel, calculating the second data based on the up-scaled second plurality of weights, and performing the first pruning.

Abstract: A method of generating a fixed-point type neural network by quantizing a floating-point type neural network, includes obtaining, by a device, a plurality of post-activation values by applying an activation function to a plurality of activation values that are received from a layer included in the floating-point type neural network, and deriving, by the device, a plurality of statistical characteristics for at least some of the plurality of post-activation values. The method further includes determining, by the device, a step size for the quantizing of the floating-point type neural network, based on the plurality of statistical characteristics, and determining, by the device, a final fraction length for the fixed-point type neural network, based on the step size.

Abstract: A method of quantizing an artificial neural network includes dividing an input distribution of the artificial neural network into a plurality of segments, generating an approximated density function by approximating each of the plurality of segments, calculating at least one quantization error corresponding to at least one step size for quantizing the artificial neural network, based on the approximated density function, and determining a final step size for quantizing the artificial neural network based on the at least one quantization error.

Abstract: A residual echo estimator estimates a residual echo of a microphone signal input to a microphone as a reference signal is output through a speaker. The residual echo estimator estimates a magnitude of a residual echo of the reference signal at a current frame by using a magnitude of the linear echo of the reference signal at the current frame and a magnitude of the linear echo of the reference signal at a past frame, and updates weights to be applied to the magnitudes of the linear echo.

Abstract: A residual echo estimator estimates a residual echo of a microphone signal input to a microphone as a reference signal is output through a speaker. The residual echo estimator estimates a magnitude of a residual echo of the reference signal at a current frame by using a magnitude of the linear echo of the reference signal at the current frame and a magnitude of the linear echo of the reference signal at a past frame, and updates weights to be applied to the magnitudes of the linear echo.

Abstract: A method and apparatus for generating a fixed point neural network are provided. The method includes selecting at least one layer of a neural network as an object layer, wherein the neural network includes a plurality of layers, each of the plurality of layers corresponding to a respective one of plurality of quantization parameters; forming a candidate parameter set including candidate parameter values with respect to a quantization parameter of the plurality of quantization parameters corresponding to the object layer; determining an update parameter value from among the candidate parameter values based on levels of network performance of the neural network, wherein each of the levels of network performance correspond to a respective one of the candidate parameter values; and updating the quantization parameter with respect to the object layer based on the update parameter value.

Abstract: An artificial neural network (ANN) quantization method for generating an output ANN by quantizing an input ANN includes: obtaining second parameters by quantizing first parameters of the input ANN; obtaining a sample distribution from an intermediate ANN in which the obtained second parameters have been applied to the input ANN; and obtaining a fractional length for the sample distribution by quantizing the obtained sample distribution.

Abstract: A method of generating a fixed-point type neural network by quantizing a floating-point type neural network, includes obtaining, by a device, a plurality of post-activation values by applying an activation function to a plurality of activation values that are received from a layer included in the floating-point type neural network, and deriving, by the device, a plurality of statistical characteristics for at least some of the plurality of post-activation values. The method further includes determining, by the device, a step size for the quantizing of the floating-point type neural network, based on the plurality of statistical characteristics, and determining, by the device, a final fraction length for the fixed-point type neural network, based on the step size.

Abstract: A method of quantizing an artificial neural network includes dividing an input distribution of the artificial neural network into a plurality of segments, generating an approximated density function by approximating each of the plurality of segments, calculating at least one quantization error corresponding to at least one step size for quantizing the artificial neural network, based on the approximated density function, and determining a final step size for quantizing the artificial neural network based on the at least one quantization error.

Abstract: Provided is a joint pattern beam sectorization method and apparatuses for performing the same, wherein the joint pattern beam sectorization method including generating, in a service target region, a pattern sector corresponding to an antenna array including antennas having an identical radiation pattern by using the antenna array and generating pattern beam sectors in the pattern sector through a beamforming using the antennas.

Abstract: Provided is a joint pattern beam sectorization method and apparatuses for performing the same, wherein the joint pattern beam sectorization method including generating, in a service target region, a pattern sector corresponding to an antenna array including antennas having an identical radiation pattern by using the antenna array and generating pattern beam sectors in the pattern sector through a beamforming using the antennas.

Abstract: A method and apparatus for improving a mobile problem caused by a narrow handover region in a boundary region between virtual cells constructed by a plurality of small base stations are provided. A plurality of Virtual Cells (VCs) include a plurality of Distributed Base Stations (DBSs) whose VCs cooperatively communicate with each other. An Intermediate Distributed Base Station (I-DBS) is located in a region where adjacent at least two VCs among the plurality of VCs are superimposed, and belongs to a different VC according to a time division scheme.

Abstract: A method and apparatus for improving a mobile problem caused by a narrow handover region in a boundary region between virtual cells constructed by a plurality of small base stations are provided. A plurality of Virtual Cells (VCs) include a plurality of Distributed Base Stations (DBSs) whose VCs cooperatively communicate with each other. An Intermediate Distributed Base Station (I-DBS) is located in a region where adjacent at least two VCs among the plurality of VCs are superimposed, and belongs to a different VC according to a time division scheme.