Sample training method for novel convolutional neural network
A convolutional neural network and sample training technology, applied in the field of neural network algorithms, can solve problems such as time consumption of neural networks, achieve the effects of improving intelligence and generalization, promoting the scope of use, and improving adaptability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0014] The technical solution of the present invention will be further described in detail below.
[0015] In order to solve the problem that the existing neural network consumes a lot of time in the sample collection and training process in the whole structure design and calculation process, the present invention provides a new convolutional neural network sample training method, the method includes the following steps :
[0016] Determine a certain number of sample sets as the benchmark data set for training, moderately distort the training weights, and set the initial learning rate and final learning rate for training;
[0017] Based on the initial learning rate, the sample set is trained using the second-order backpropagation learning algorithm, and the training ends when the learning rate reaches the final learning rate.
[0018] In the process of using the second-order backpropagation algorithm, an error will be generated. The partial derivative of the error is equal to...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 