Machine learning specializes in studying how computers can simulate or implement human learning behavior to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their own performance. Problems that machine learning can solve: 1. Classification problems; 2. Regression problems; 3. Clustering problems.
The operating environment of this tutorial: Windows 7 system, Dell G3 computer.
What is machine learning?
Machine learning is to learn part of the computer data, and then predict and judge other data.
The core of machine learning is "using algorithms to parse data, learn from it, and then make decisions or predictions about new data." That is to say, the computer uses the data obtained to derive a certain model, and then uses this model to make predictions. This process is somewhat similar to the human learning process. For example, after a person acquires certain experience, he or she can predict new problems.
Let’s give an example. We all know that Alipay’s Spring Festival “Collect Five Blessings” activity. We use our mobile phones to scan photos of the word “福” to identify the word “福”. This uses machine learning methods. We can provide the computer with photo data of the word "福". Through algorithm model training, the system continuously updates and learns, and then inputs a new photo with the word "福", and the machine automatically identifies whether there is the word "福" on the photo.
Machine learning is a multi-field interdisciplinary subject involving probability theory, statistics, computer science and other disciplines. The concept of machine learning is to train the model by inputting massive training data, so that the model can grasp the potential patterns contained in the data, and then accurately classify or predict the newly input data. As shown in the figure below:
#What kind of problems can machine learning solve?
Classification from a functional perspective, machine learning can solve the following problems on a certain level of data:
1. Classification problem: According to the features extracted from the data samples, Determine which of a limited number of categories it belongs to. For example: spam identification (result category: 1. Spam 2. Normal mail).
2. Regression problem: predict the result of a continuous value based on the features extracted from the data sample. For example: Xing Ye's "Mermaid" box office
3. Clustering problem: According to the characteristics extracted from the data samples, the samples are grouped together (similar/related samples are in a group). For example: Google's news classification.
Let’s divide the above common problems into the two most typical categories of machine learning.
Classification and regression problems need to be trained with data with known results. Problems that belong to "supervised learning"
Clustering problems do not need to be Know the label, it belongs to "unsupervised learning".
If you take a walk in the IT industry (especially the Internet), you will find that machine learning is widely used in the following hot issues:
For more related knowledge, please visit theFAQcolumn!
The above is the detailed content of What is machine learning? What kind of problems can machine learning solve?. For more information, please follow other related articles on the PHP Chinese website!