Machine abnormity processing method, learning rate adjusting method and device
A technology of learning rate and processing method, applied in the Internet field, can solve problems such as high training cost, slow calculation or communication speed, machine abnormality processing method, learning rate, etc., and achieve the effect of solving high training cost and reducing training cost.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0026] According to the embodiment of the present application, a method embodiment of a method for processing machine exceptions is also provided. It should be noted that the steps shown in the flow charts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions , and, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.
[0027] The method embodiment provided in Embodiment 1 of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Take running on a computer terminal as an example, figure 1 It is a block diagram of the hardware structure of a computer terminal according to a method for processing machine abnormality in the embodiment of the present application. Such as figure 1 As shown, the computer terminal 10 may include one or more (only...
Embodiment 2
[0058] According to the embodiment of the present application, a method embodiment of a method for adjusting the learning rate is also provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions , and, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.
[0059] This application provides Figure 4 The tuning method for the learning rate is shown. Figure 4 It is a flow chart of the learning rate adjustment method according to Embodiment 2 of the present application.
[0060] Step S402, obtaining the gradient calculated by the target machine.
[0061] In step S402 of this application, the gradient is the value obtained after deriving the loss function. The loss function is a method that maps an event (an element in a sample space) to an...
Embodiment 3
[0076] According to the embodiment of the present application, a device embodiment for implementing the above embodiment of the processing method for machine abnormality is also provided, and the device provided by the above embodiment of the present application can be run on a computer terminal.
[0077] Figure 5 is a schematic structural diagram of a machine abnormality processing device according to an embodiment of the present application.
[0078] Such as Figure 5 As shown, the device for processing machine abnormalities may include a first acquiring unit 502 , a judging unit 504 and a detecting unit 506 .
[0079] Wherein, the first acquiring unit 502 is configured to acquire the gradient consumption time of the target machine, wherein the gradient consumption time is used to represent the gradient-related time consumed by the target machine during the training process; the judging unit 504 is configured to Judging whether the gradient consumption time satisfies a pr...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More