About this slide, do I understand correct, that w will aim to zero and grade neuron influence only in cases, when this w was low before? So, when W was high neuron will left and regularization only will reduce w a bit in this neuron? But it was presented like something that is firstly for high weigh…

Will only low weights aim to zero with regularization

saifkhanengr May 9, 2023, 3:07pm 4

Regularization is different from cost. Check my reply to your different post.

Topic		Replies	Views
Why does regularization reduce w? Improving Deep Neural Networks: Hyperparameter tun	7	585	August 18, 2023
Learning rate on Regularization Supervised ML: Regression and Classification week-3	5	337	December 21, 2023
Will Lambda reduce the size of the w parameters? Supervised ML: Regression and Classification week-3	7	492	May 6, 2023
About Regularization , can we increase weights instead of decreasing it to address overfitting Supervised ML: Regression and Classification week-3	4	507	November 1, 2022
Why W will close to 0 when lambd? Improving Deep Neural Networks: Hyperparameter tun	6	513	August 19, 2022