Basics of Neural Network Programming - Binary Classification

This article is the notes when I learn the class "Neural Networks & Deep Learning" by teacher Andrew Ng. It shows info of Binary classification which is the basics of Neural Network Programming. Shares it with you and hope it helps.

---

Here's an example of a binary classification problem.

Figure-1

You might have an input of an image like the left of figure-1, and want to output a label to recognize this image as being either a cat (y=1) or non-cat (y=0).

Let's look at how an image is represented in a computer. An image is store in the computer in three separate matrices corresponding to the Red, Green, and Blue color channels of the image (as the right of figure-1). The three matrices have the same size as the image. For example, the resolution of the cat image is 64 pixels X 64 pixels, the three matrices (RGB) are 64 X 64 each (Note:5 x 4 only for demo purpose). The value in a cell represents the pixel intensity which will be used to create a feature vector of n-dimension.

Figure-2

Logistic regression is an algorithm of binary classification. To use logistic regression, we need create a feature vector, 𝑥. The pixel intensity values will be “unroll” or “reshape” for each color, as shown in figure-2. The dimension of the input feature vector 𝑥 is .

In binary classification, the goal is to train a classifier that the input is an image represented by a feature vector, 𝑥, and predicts whether the corresponding label 𝑦 is 1 or 0. In this case, whether this is a cat image (1) or a non-cat image (0).

Let's now lay out some of the notations we'll use next:

<end>