Unlock instant, AI-driven research and patent intelligence for your innovation.

Adaptive bit-width reduction for neural networks

A neural network and neural network model technology, applied in the field of machine learning real-time applications, can solve problems such as limiting hardware upgrades and compromising model accuracy

Active Publication Date: 2020-02-14
MIDEA GRP CO LTD
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Model reduction, which focuses on reducing the complexity of the model structure, often greatly impairs the accuracy of the model, while practical cost and energy consumption issues limit hardware upgrades

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Adaptive bit-width reduction for neural networks
  • Adaptive bit-width reduction for neural networks
  • Adaptive bit-width reduction for neural networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] Reference will now be made in detail to the embodiments, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the various embodiments described. It will be apparent, however, to one of ordinary skill in the art that various described embodiments may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

[0014] It will also be understood that, although the terms first, second etc. are used in some instances herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first layer could be termed a second layer, and, similarly, a layer could be termed a f...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method of providing an adaptive bit-width neural network model on a computing device, comprising: obtaining a first neural network model, wherein each layer of first neural network model has a respective set of parameters expressed with an original bit-width of the first neural network model; reducing a footprint of the first neural network model by using respective reduced bit-widths for storing the respective sets of parameters of different layers of the first neural network model, wherein: preferred values of the respective reduced bit-widths are determined through multiple iterations offorward propagation through the first neural network model using a validation data set while each of two or more layers of the first neural network model is expressed with different degrees of quantization until a predefined information loss threshold is met; and generating a reduced neural network model with quantized parameters expressed with the respective reduced bit-widths.

Description

technical field [0001] The present disclosure relates to machine learning real-time applications, and more particularly, to improving machine learning models for portable devices and real-time applications by reducing the model size and computational footprint of the machine learning models while maintaining the same accuracy. Background technique [0002] Machine learning has broad applicability in many fields, including computer vision, speech recognition, machine translation, social network filtering, board and video games, medical diagnosis, and many others. A machine learning model such as an artificial neural network (ANN) is a network of simple units (neurons) that receive input, change their internal state (activation) based on that input, and produce output based on the input and activation. The network is formed by connecting the outputs of certain neurons to the inputs of other neurons through directed weighted graphs. The weights and the function to calculate th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04
CPCG06N3/063G06N3/084G06N3/082G06N3/045G06N3/08G06N3/04G06N3/006
Inventor 王奥森周华陈昕
Owner MIDEA GRP CO LTD