Classification is a type of supervised learning. We need a machine learning model in order to predict the correct label for a new instance. For example, the handwritten image recognition problem is categorized as a classification problem. The most popular dataset for handwritten digits is MNIST. MNIST was developed by Yann LeCun, who won the Turing award in 2018 for leading the current boom of artificial intelligence research. This is the prediction result when using TensorFlow.js:
While handwritten digit classification is a multi-label classification problem, the problem we are going to solve in this chapter is binary classification. The target labels to be predicted in the binary classification situation have only two labels: positive and negative. In the following example, there are two classes: a set of rhombuses and circles. If these two...
