Index.html

1.1 Visualizing the dataTo help you get more familiar with plotting, we have left plotData.m empty so you can try to implement it yourself. However, this is an optional(ungraded) exercise. We also prov

1 InitIn the file warmUpExercise.m, you will find the outline of an Octave/MATLAB function. Modify it to return a 5x5 identity matrix by lling in the following code:A = eye(5);2.1 Plotting the DataBe

1.2 Regularized linear regression cost functionRecall that regularized linear regression has the following cost function:J(θ)=12m(∑mi=1(hθ(x(i))−y(i))2)+λ2m(∑nj=1θ2j)J(\theta )=\frac{1}{2m}(\sum_{i=1}^

1.3.3 Vectorizing regularized logistic regressionNow modify your code in lrCostFunction.m to account for regularization.Once again, you should not put any loops into your code. 此处参考上一周加入正则化的逻辑回归代码即可。n

1.3 Feedforward and cost functionRecall that the cost function for the neural network (without regularization) is J(θ)=1m∑mi=1∑Kk=1[−y(i)klog((hθ(x(i)))k)−(1−y(i)k)log(1−(hθ(x(i)))k)]J(\theta ) = \fra

1.2 SVM with Gaussian KernelsYou should now complete the code in gaussianKernel.m to compute the Gaussian kernel between two examples, (x(i); x(j)). The Gaussian kernel function is dened as:Kgaussian(

1.1.1 Finding closest centroidsYour task is to complete the code in findClosestCentroids.m. This function takes the data matrix X and the locations of all centroids inside centroids and should output a

转载自：http://blog.youkuaiyun.com/zy3381/article/details/44409535 CNN(卷积神经网络)的误差反传(error back propagation)中有一个非常关键的的步骤就是将某个卷积(Convolve)层的误差传到前一层的池化(Pool)层上，因为在CNN中是2D反传，与传统神经网络中的1D反传有点细节上的不同，下面通过一个简单的例子来详细分解一

1 Anomaly DetectionYour task is to complete the code in estimateGaussian.m. This function takes as input the data matrix X and should output an n-dimension vector mu that holds the mean of all the n fe