Location:Training / Machine Learning/Algorithm / Machine learning from zero to one / Building an image classifier

You'll learn that machine learning is a new area of ​​programming. Using traditional programming languages, such as Java or C++, to write a program requires the use of clear rules. Machine learning can infer these rules through training data. But what does machine learning actually look like? In the first episode of the video series, Fei Ying will use a simple sample code to build a machine learning model and introduce some basic concepts. We will apply these concepts in subsequent videos to solve a more interesting problem: computer Vision.

In the second episode of the video series, Fei Ying will teach us some basic computer vision concepts through examples of how to train computers to see and recognize different objects.

In the third episode of this video series, Fei Ying discusses convolutional neural networks and why they are widely used in computer vision. Convolution is an image filter. It can be used to extract common features in input images. In this video, you'll learn how it works by processing an input image to see if you can extract features from it.
In the fourth episode of the video series, Fei Ying discusses how to build a rock-paper-scissors classifier. In the first episode, we used this example to show how difficult it is to detect and classify them using traditional code. As we move deeper into machine learning, we've learned how to build neural networks: from detecting patterns in raw pixels, to classifying them, to detecting features using convolutions. In this episode, we pull together everything from the first three episodes of the series.