Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Вопрос о backpropagation #9

Closed
sdshorin opened this issue Nov 1, 2020 · 0 comments
Closed

Вопрос о backpropagation #9

sdshorin opened this issue Nov 1, 2020 · 0 comments

Comments

@sdshorin
Copy link

sdshorin commented Nov 1, 2020

https://github.com/Elco-/SimpleNN/blob/a293af6d939bf4ed2680314a24769c594b4fa087/src/NeuralNetwork.java#L62

Спасибо тебе за твой труд, использую его как шпаргалку, пока изучаю нейросети.
Такой вопрос.

            for (int i = 0; i < l1.size; i++) {
                for (int j = 0; j < l.size; j++) {
                    deltas[i][j] = gradients[i] * l.neurons[j];
                }
            }

Здесь точно должно быть умножение, а не деление? Ведь у нас есть функция x*w=y. Мы знаем, что хотим изменить y на g. x*w=y+g -> (x*w)-g=y-> x*(w - g/x)=y
Получается, должно быть deltas[i][j] = gradients[i] / l.neurons[j];?

@sdshorin sdshorin closed this as completed Nov 9, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant