Shulou(Shulou.com)06/02 Report--

I would like to share with you the relationship among artificial intelligence, machine learning and deep learning. I believe most people don't know much about it, so share this article for your reference. I hope you will learn a lot after reading this article. Let's learn about it!

Machine learning is a subset of artificial intelligence, which includes technologies that enable computers to identify problems from data and deliver artificial intelligence applications. Deep learning is a subset of machine learning, which enables computers to solve more complex problems.

I. artificial intelligence

Artificial intelligence (Artificial Intelligence), abbreviated as AI. It is a new technical science that studies and develops theories, methods, technologies and application systems used to simulate, extend and expand human intelligence.

Artificial intelligence is a branch of computer science, which attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. research in this field includes speech recognition, image recognition, robots, natural language processing, intelligent search and expert systems.

Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is not human intelligence, but it may surpass human intelligence if it can think like human beings.

Second, data mining

Data mining (Data Mining), as its name implies, is to "mine" hidden information from massive data. According to the textbook, the data here is "massive, incomplete, noisy, fuzzy and random practical application data". Information refers to "hidden, regular, unknown, potentially useful and ultimately understandable information and knowledge". In a business environment, enterprises want to make the data stored in the database "talk" and support decision-making. Therefore, data mining is more inclined to the application.

Data mining is usually related to computer science, and the above goals are achieved through statistics, online analytical processing, information retrieval, machine learning, expert systems (relying on past rules of thumb), pattern recognition and many other methods.

III. Machine learning

Machine learning (Machine Learning) refers to the process of using some algorithms to guide the computer to obtain an appropriate model using known data, and using this model to judge the new situation.

The idea of machine learning is not complicated, it is only a simulation of the learning process in human life. In the whole process, the most important thing is the data.

Any research on learning algorithms trained by data belongs to machine learning, including many techniques that have been developed for many years, such as linear regression (Linear Regression), K-means (K-means, prototype-based objective function clustering method), decision tree (Decision Trees, a graphical method of probability analysis), random forest (Random Forest, a graphical method of probability analysis), PCA (Principal Component Analysis). Principal component analysis, SVM (Support Vector Machine, support vector machine) and ANN (Artificial Neural Networks, artificial neural network).

IV. In-depth learning

The concept of deep learning (Deep Learning) originates from the research of artificial neural network. Multi-layer perceptrons with multiple hidden layers are a kind of deep learning structure. Deep learning combines low-level features to form more abstract high-level representation attribute categories or features to discover the distributed feature representation of data.

Deep learning is a new field of machine learning, its motivation is to establish and simulate the human brain for analytical learning neural network, which imitates the mechanism of the human brain to interpret data, such as images, sounds and texts.

V. the relationship between artificial intelligence, machine learning and deep learning

Strictly speaking, there is no direct relationship between artificial intelligence and machine learning, but the current methods of machine learning are widely used to solve the problem of artificial intelligence. At present, machine learning is not only a way to realize artificial intelligence, but also the most important way to achieve it.

Early machine learning actually belonged to statistics, not computer science, and the classical artificial intelligence before the 1990s had nothing to do with machine learning. So today's AI and ML have a lot of overlap, but there is no strict affiliation.

However, only within the computer department, ML belongs to AI. AI has become a very general discipline today.

Deep learning is a popular direction of machine learning, which is a derivative of neural network algorithm, and has achieved very good results in the classification and recognition of rich media such as images, speech and so on.

Therefore, if you look at artificial intelligence and machine learning as two disciplines, the relationship between them is shown in the following figure:

If you think of deep learning as a subdiscipline of artificial intelligence, the relationship between the three is shown in the following figure:

VI. The relationship between data Mining and Machine Learning

Data mining mainly uses the technology provided by the machine learning community to analyze the massive data, and uses the technology provided by the database community to manage the massive data.

Machine learning is an important method of data mining, but machine learning is another subject, which does not belong to data mining.

Add:

Source: http://m.elecfans.com/article/691751.html

The machine learning process is defined using the following steps:

1. Identify relevant data sets and prepare for analysis.

two。 Select the type of algorithm you want to use.

3. Build the analysis model according to the algorithm used.

4. The model is trained based on the test data set, and the model is modified as needed.

5. Run the model to generate test scores.

The difference between machine learning and deep learning

1. Amount of data:

Machine learning can adapt to various amounts of data, especially in scenarios with small amounts of data. On the other hand, if the amount of data increases rapidly, then the effect of deep learning will be more prominent. The following figure shows the efficiency of machine learning and deep learning under different data volumes.

two。 Hardware dependencies:

Contrary to the traditional machine learning algorithm, the design of deep learning algorithm is highly dependent on high-end equipment. Deep learning algorithm needs to perform a large number of matrix multiplication operations, so it needs sufficient hardware resources to support it.

3. Feature Engineering:

Feature engineering is the process of putting specific domain knowledge into specified features, which aims to reduce the level of data complexity and generate patterns that can be used to learn algorithms.

Example: traditional machine learning models focus on finding pixels and other attributes needed in feature engineering. The deep learning algorithm focuses on other advanced features of the data, so it can reduce the actual workload of the feature extractor when dealing with each new problem.

4. Problem solving method

Traditional machine learning algorithms follow standard procedures to solve problems. It divides the problem into several parts, solves them separately, and then combines the results to get the desired answer. Deep learning solves problems in a centralized manner without the need for problem splitting.

5. Execution time

Execution time refers to the amount of time required to train the algorithm. Deep learning requires a lot of time for training, because it contains more parameters, so the time investment in training is more considerable. Relatively speaking, the execution time of machine learning algorithm is relatively short.

6. Interpretable

Interpretability is one of the main differences between machine learning and deep learning algorithms-deep learning algorithms often do not have interpretability. Because of this, the industry always thinks twice before using deep learning.

Practical application of machine learning and deep learning:

The computer vision technology of punching in attendance, face recognition or license plate recognition by scanning the license plate is realized by fingerprint.

Information retrieval functions in search engines, such as text search and image search.

Automatic email marketing and specific target recognition.

Identification of abnormal states in cancer, oncology, medical diagnosis or other chronic diseases.

Natural language processing applications, such as photo tags. Facebook provides such features to enhance the user experience.

Online advertising.

Future development trend:

With the increasing use of data science and machine learning technologies in the industry, it is most important for organizations to introduce machine learning solutions into their existing business processes.

The importance of deep learning is gradually surpassing machine learning. It has been proved that deep learning is one of the most advanced and effective technical solutions at present.

Machine learning and deep learning will prove their great energy in the research and academic fields.

These are all the contents of this article entitled "what is the relationship between artificial intelligence, machine learning and deep learning". Thank you for reading! I believe we all have a certain understanding, hope to share the content to help you, if you want to learn more knowledge, welcome to follow the industry information channel!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.