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: 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 neural network optimizing device includes a performance estimating module that outputs estimated performance according to performing operations of a neural network based on limitation requirements on resources used to perform the operations of the neural network. A portion selecting module receives the estimated performance from the performance estimating module and selects a portion of the neural network which deviates from the limitation requirements. A new neural network generating module generates, through reinforcement learning, a subset by changing a layer structure included in the selected portion of the neural network, determines an optimal layer structure based on the estimated performance provided from the performance estimating module, and changes the selected portion to the optimal layer structure to generate a new neural network. A final neural network output module outputs the new neural network generated by the new neural network generating module as a final neural network.

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: A user adaptive image compensator includes a feature extractor, a compensated image generator, an image selector, and a preference parameter updater. The feature extractor extracts features from an input image. The compensated image generator generates compensated preference parameters based on a preference parameter. The compensated image generator generates a plurality of compensated images by compensating the input image based on the compensated preference parameters. The image selector displays the compensated images to a user. The image selector outputs a selected compensated image, which is selected from the compensated images by the user, as an output image. The image selector outputs a selected compensated preference parameter from the compensated preference parameters and which corresponds to the selected compensated image. The preference parameter updater updates the preference parameter based on the selected compensated preference parameter and the extracted features.

Abstract: At least one example embodiment discloses a method of detecting an object in an image. The method includes receiving an image, generating first images for performing a first classification operation based on the received image, reviewing first-image features of the first images using a first feature extraction method with first-type features, first classifying at least some of the first images as second images, the classified first images having first-image features matching the first-type features, reviewing second-image features of the second images using a second feature extraction method with second-type features, second classifying at least some of the second images as third images, the classified second images having second-image features matching the second-type features and detecting an object in the received image based on results of the first and second classifying.

Abstract: A user adaptive image compensator includes a feature extractor, a compensated image generator, an image selector, and a preference parameter updater. The feature extractor extracts features from an input image. The compensated image generator generates compensated preference parameters based on a preference parameter. The compensated image generator generates a plurality of compensated images by compensating the input image based on the compensated preference parameters. The image selector displays the compensated images to a user. The image selector outputs a selected compensated image, which is selected from the compensated images by the user, as an output image. The image selector outputs a selected compensated preference parameter from the compensated preference parameters and which corresponds to the selected compensated image. The preference parameter updater updates the preference parameter based on the selected compensated preference parameter and the extracted features.

Abstract: At least one example embodiment discloses a method of detecting an object in an image.