Coursera Wunda Machine Learning Course Summary notes and work Code-5th week neural network continued

Neural networks:learning

Last week's course learned the neural network forward propagation algorithm, this week's course mainly lies in the neural network reverse renewal process. 1.1 Cost function

Let's recall the value function of logistic regression.
J (θ) =1m[∑mi=1y (i) log (hθ (x (i)) + (1−y (i)) log (1−hθ (x (i)))]+λ2m∑nj=1θ2j J (\theta) = \frac{1}{m}[\sum_{i=1}^{m}y^{(i)} Log (H_\theta (x^{(i))) + (1-y^{(i)}) log (1-h_\theta (x^{(i)})) + \frac{\lambda}{2m}\sum_{j=1}^{n}\theta_j^2

In the neural network
hθ (x) Εrk H_\theta (x) \epsilon r^k (hθ (x)) I=ithoutput (H_\theta (x)) _i = I^{th}output
J (θ) =−1m[∑mi=1∑kk=1y (i) Klog (hθ (x