Samsung Electronics Co., Ltd.

Seoul National University

Soonhoi Ha

Donghyun Kang

Jintaek Kang

Yoojin Kim

Hyunsun Park

Hanwoong Jung

Duseok Kang

A processor-implemented method of a neural network includes obtaining intermediate pooling results, respectively corresponding to sub-pooling kernels obtained by decomposing an original pooling kernel, by performing a pooling operation on input pixels included in a current window in an input feature map with the sub-pooling kernels, obtaining a final pooling result corresponding to the current window by post-processing the intermediate pooling results, and determining an output pixel value of an output feature map, based on the final pooling result, wherein the current window is determined according to the original pooling kernel having been slid, according to a raster scan order, in the input feature map.

Neural processing apparatus and method with neural network pool processing

A neural network operation apparatus and method are disclosed. The neural network operation apparatus may include an adder configured to perform addition of data for performing a neural network operation and main data, a first multiplexer configured to output one of an output result of the adder and the main data based on a reset signal, a second multiplexer configured to output one of the main data and a quantization result of the data based on a phase signal, and a controller configured to control the first and second multiplexers by generating the reset signal and the phase signal.

Apparatus and method with neural network operation

A processor-implemented neural network method includes: generating a bit vector based on whether each of a plurality of input activations within a neural network is 0; merging the bit vector into the input activations such that bit values within the neural network included in the bit vector are most significant bits (MSBs) of multi bit expressions of the input activations; merging the bit vector into weights such that the bit values included in the bit vector are MSBs of multi bit expressions of the weights; sorting the input activations and the weights based on bits corresponding to the MSBs; and implementing the neural network, including performing operations between the sorted input activations and the sorted weights.

Method and apparatus with neural network operation

Growing community of inventors

Seoul, South Korea

Soonhoi Ha