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

Efficient binary representations from neural networks

A neural network and function technology, applied in biological neural network models, neural architectures, neural learning methods, etc., can solve problems such as resource constraints and inability to obtain results from models

Pending Publication Date: 2021-12-21
GOOGLE LLC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the other hand, devices with limited memory, processing power, and battery life, such as laptops, tablets, and smart mobile phones, remain resource constrained
These limited devices may not be able to obtain results from the trained model within a reasonable time frame or at all

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
  • Efficient binary representations from neural networks
  • Efficient binary representations from neural networks
  • Efficient binary representations from neural networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Example methods, devices, and systems are described herein. It should be understood that the words "example" and "exemplary" are used herein to mean "serving as an example, instance, or illustration." Any embodiment or feature described herein as "example" or "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or features, unless so stated. Accordingly, other embodiments may be utilized and other changes may be made without departing from the scope of the subject matter presented herein.

[0029] Therefore, the example embodiments described herein are not meant to be limiting. It will be readily understood that the various aspects of the disclosure, generally described herein and shown in the drawings, can be arranged, substituted, combined, separated and designed in a wide variety of different configurations. For example, the separation of features into "client" and "server" components can happen in a variety of ways.

...

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

Persistent storage contains a representation of a neural network including an input layer, and output layer, and a hidden layer, wherein nodes of the hidden layer incorporate serialized activation functions, wherein the serialized activation functions for each of the nodes include a sigmoid function and a Beta function, wherein the sigmoid function is applied to weighted outputs from nodes of a previous layer of the neural network, wherein the Beta function is applied to a conductance hyper-parameter and respective outputs of the sigmoid function, and wherein outputs of the Beta function are provided to a subsequent layer of the neural network. One or more processors are configured to train the neural network until the outputs of the sigmoid function for the nodes of the hidden layer are substantially binary.

Description

Background technique [0001] With the dramatic increase in the processing power of server devices and the availability of large datasets for training, machine learning models have become larger and more complex. For example, deep neural networks are now being used to solve problems in natural language processing, image processing, computer vision, robotics, and medical care. Due to the size of these neural networks and the extent and quality of the training data, it is now possible to deliver results that were previously unobtainable. On the other hand, devices with limited memory, processing power, and battery life, such as laptop computers, tablet computers, and smart mobile phones, remain resource constrained. These limited devices may not be able to obtain results from the trained model within a reasonable time frame or at all. Contents of the invention [0002] A neural network may include multiple layers of nodes, each node in a layer outputting a value that is the re...

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): G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06N3/047G06N3/048G06N3/044G06N3/088
Inventor R.麦克唐纳L.萨门托
Owner GOOGLE LLC