Weight threshold correction-reverse Propagation

Source: Internet
Author: User

0 network computing results

B (M) = f (Σ N (w (n, m) * x (n)-percentile (M) % output of the intermediate layer

Y (K) = f (Σ M (V (M, k) * B (M)-percentile (k) % output of the output layer

1. Calculate the error value

E (K) = y' (k)-y (k) % y' indicates the actual output value of the sample.

2. Calculate the calibration error

DV (K) = E (k) * Y (k) * (1-Y (k ))

DW (m) = Σ K (DV (k) * V (M, k) * B (M) * (1-B (m ))

3. Error Correction

V (M, K) = V (M, k) + DV (k) * B (M) * [learning rate]

W (n, m) = W (n, m) + DW (m) * x (n) * [learning rate]

Round (K) = round (k) + DV (k) * [learning rate]

Average (m) = average (m) + DW (m) * [learning rate]

Weight threshold correction-reverse Propagation

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.