Information processing apparatus, information processing method, and recording medium
A technology of information processing device and information processing method, which is applied in the direction of neural learning method, biological neural network model, program control, etc., can solve the problem of not considering the transmission control of the detection state data collection device, and not considering the communication cost and discrimination accuracy The ebb and flow, did not take into account the self-discipline distributed sensor terminal transmission control reinforcement learning and other issues
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 Embodiment approach >
[0053] >
[0054] First, the first embodiment of the present invention will be described. As described above, the present invention can simultaneously realize the maintenance of the discrimination accuracy and the suppression of the communication cost in the state discrimination of the observation target based on the sensor information acquired by the plurality of sensor terminals.
[0055] figure 1 It is a figure which shows an example of the system structure of this embodiment. Reference figure 1 The information processing system of this embodiment may include an observation target 10, a plurality of sensor terminals 20, and an information processing device 30. In addition, the sensor terminal 20 and the information processing device 30 are connected via a network 40.
[0056] (Observed object 10)
[0057] The observation target 10 of the present embodiment is a target for which the information processing device 30 performs state discrimination. The observation target 10 in this ...
no. 2 Embodiment approach >
[0160] >
[0161] Next, the second embodiment of the present invention will be described. The second embodiment of the present invention is the same as the first embodiment, and aims to achieve optimization of the discrimination accuracy and communication cost in the state discrimination of the observation object 10 based on sensor information. On the other hand, the second embodiment of the present invention differs from the first embodiment in that it focuses on constructing a value function in a state where reinforcement learning cannot be clearly defined.
[0162] For example, it can also be assumed that when the number of sensor terminals 20 and sensors 210 is large, it is difficult to construct a learning model that includes all combinations. In addition, it can also be assumed that the exact same value is rarely obtained depending on the nature of the sensor information. Therefore, the information processing device 30 of the present embodiment can approximate the value fun...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


