Artificial neural network apparatus and operating method for the same

Patent metadata

Field	Value
Publication number	US-11488003-B2
Application number	US-201916409437-A
Country	US
Kind code	B2
Filing date	May 10, 2019
Priority date	May 23, 2018
Publication date	Nov 1, 2022
Grant date	Nov 1, 2022

Abstract

An artificial neural network apparatus and an operating method including a plurality of layer processors for performing operations on input data are disclosed. The artificial neural network apparatus may include: a flag layer processor for outputting a flag according to a comparison result between a pooling output value of a current frame and a pooling output value of a previous frame; and a controller for stopping operation of a layer processor which performs operations after the flag layer processor among the plurality of layer processors when the flag is outputted from the flag layer processor, wherein the flag layer processor is a layer processor that performs a pooling operation first among the plurality of layer processors.

First claim

What is claimed is:

1. An artificial neural network apparatus including a plurality of layer processors for performing operations on input data, comprising:
a flag layer processor for outputting a flag according to a comparison result between a pooling output value of a current frame and a pooling output value of a previous frame; and
a controller for stopping operation of a layer processor which performs operations after the flag layer processor among the plurality of layer processors, when the flag is outputted from the flag layer processor,
wherein the flag layer processor is a layer processor that performs a pooling operation first among the plurality of layer processors.

2. The artificial neural network apparatus of claim 1 , wherein
the flag layer processor outputs the flag when the pooling output value of the current frame is equal to the pooling output value of the previous frame.

3. The artificial neural network apparatus of claim 1 , wherein
the pooling output value of the current frame and the pooling output value of the previous frame are position information stored according to a comparison result between a pooling operation value and a previously stored reference value.

4. The artificial neural network apparatus of claim 1 , wherein
the flag layer processor includes a memory for storing the pooling output value of the current frame and the pooling output value of the previous frame.

5. The artificial neural network apparatus of claim 1 , further comprising:
a comparator for comparing the pooling output value of the current frame with the pooling output value of the previous frame, and outputting the flag when the pooling output value of the current frame and the pooling output value of the previous frame are the same.

6. An artificial neural network apparatus including a plurality of layer processors for performing operations on input data, comprising:
a flag layer processor for outputting a flag when position information of a current frame and position information of a previous frame respectively stored in accordance with comparison results between pooling operation values and previously stored reference values are the same; and
a controller for stopping operation of a layer processor which performs operations after the flag layer processor among the plurality of layer processors when the flag is outputted from the flag layer processor,
wherein the flag layer processor is a layer processor that performs a pooling operation first among the plurality of layer processors.

7. An operating method of an artificial neural network apparatus including a plurality of layer processors for performing operations on input data, comprising:
outputting a flag according to a comparison result between a pooling output value of a current frame and a pooling output value of a previous frame; and
stopping operation of a layer processor which performs operations after the flag layer processor among the plurality of layer processors when the flag is outputted from the flag layer processor.

8. The operating method of claim 7 , wherein
the outputting a flag outputs the flag when the pooling output value of the current frame is equal to the pooling output value of the previous frame.

9. The operating method of claim 7 , wherein
the outputting a flag performs operations on input data, stores pooling output values according to a comparison result between a pooling operation value and a previously stored reference value, and outputs the flag according to a comparison result between the stored pooling output value of the current frame and the stored pooling output value of the previous frame.

Assignees

• Electronics & Telecommunications Res Inst

Inventors

• Kim Ju-Yeob
• Kim Byung Jo
• Kim Seong Min
• Kim Jin Kyu
• Lee Mi Young
• Lee Joo Hyun

Classifications

• G06N3/045 Primary

  Combinations of networks · CPC title

• G06V10/82

  using neural networks · CPC title

• G06N3/063 Primary

  using electronic means · CPC title

• G06N3/04 Primary

  Architecture, e.g. interconnection topology · CPC title

• G06F9/30021

  Compare instructions, e.g. Greater-Than, Equal-To, MINMAX · CPC title