Processing method for machine abnormality, learning rate adjustment method and device
A technology of learning rate and processing method, applied in the Internet field, can solve problems such as high training cost, machine exception handling method, learning rate, slow calculation or communication speed, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0040] According to the present application embodiment, a method of providing a method of processing a method of an abnormality is provided, and it is to be described, it is to be described in the flowchart of the flowcharts shown in the drawings, can be performed in a computer system such as a set of computer executable instructions. And, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in the order herein.
[0041] The method embodiment of the present application embodiment can be performed in a mobile terminal, a computer terminal, or a similar computing device. Take it in the computer terminal, figure 1 It is a hardware configuration block diagram of a computer terminal of a machine abnormality of the embodiment of the present application. like figure 1 As shown, the computer terminal 10 can include one or more (only one shown in the figure) processor 102 (processor 102 can include, but is not limited to, micropro...
Embodiment 2
[0080] According to the present application embodiment, a method embodiment of a method of adjusting a method of learning is also provided, and it is to be explained that the steps shown in the drawings can be performed in a computer system such as a set of computer executable instructions. And, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in the order herein.
[0081] This application provides Figure 4 The method of adjustment of the learning rate shown. Figure 4 It is a flow chart of the adjustment method of the learning rate of the second embodiment of the present application.
[0082] Step S402, obtain the gradient calculated by the target machine.
[0083] In step S402, the gradient is a value obtained after the loss function. The loss function is a cost or opportunity cost that maps an event (one element in a sample space) to an economic cost or opportunity cost related to its event. A function on the real n...
Embodiment 3
[0098] According to the present application embodiment, an apparatus embodiment for performing a method of treating the above-described machine abnormality is provided, and the apparatus provided by the present application can operate on the computer terminal.
[0099] Figure 5 It is a schematic structural diagram of a processing apparatus according to the machine abnormality according to the embodiment of the present application.
[0100] like Figure 5 As shown, the processing device of the machine can include a first acquisition unit 502, a determination unit 504, and a detecting unit 506.
[0101] Among them, the first acquisition unit 502 is used to acquire the gradient time consumption time of the target machine, wherein the gradient consumption time is used to indicate the target machine to consume a gradient correlation time during the training process; judgment unit 504 for It is determined whether the gradient consumption time and the pre-acquired consumption time mean s...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More