News classification
Contact us
- Add: No. 9, North Fourth Ring Road, Haidian District, Beijing. It mainly includes face recognition, living detection, ID card recognition, bank card recognition, business card recognition, license plate recognition, OCR recognition, and intelligent recognition technology.
- Tel: 13146317170 廖经理
- Fax:
- Email: 398017534@qq.com
The difference between machine learning and artificial intelligence
The difference between machine learning and artificial intelligence
Intelligence is the ability to rationally consider and control behavior. Humans have the wisdom to consider and apply common sense to make decisions. Artificial intelligence is a research area for constructing intelligent agents. Therefore, the artificial intelligence we build in the future can be considered and acted rationally like humans. The Turing Test was proposed by Alan Turing (1950) to provide an appreciable definition of smart operations. If the robot has the following functions, it can be tested by Turing:
1. After understanding and writing natural speech and people;
2. Learning representation (know how to present knowledge to users);
3. Learning reasoning (knowing how to infer answers from stored knowledge to answer humans);
4. Machine learning inferred form and adapt to the new environment.
In short, AI is the study of rules and algorithms that help to build smart machines. The set of issues handled by AI is NP-complete.
Artificial intelligence is a universal research area that touches on five important disciplines:
1. Expert system;
2. Neural network;
Vague system
4. Robots;
5. Natural speech treatment.
Machine Learning (ML)
Machine learning is a subset of artificial intelligence. It learns data from an algorithm and obtains some data that humans require. Learning can turn people into geniuses and allow them to adapt to the new environment. Similarly, machine learning can make it strong enough to adapt to the new environment. The purpose of any machine learning algorithm is to maximize its purpose through the learning process so that it can dispose of invisible data.
The two key learning methods (algorithms) that complete machine learning are:
1. Monitor learning: External designer or logo data helps machine learning.
2. No monitoring learning: There is no tag data or external designer when learning the machine.
The purpose of artificial intelligence is to make the machine as intelligent as humans.
expert system
Expert systems are systems that rely on knowledge banks to deal with problems. The knowledge base can be represented in different ways, such as rules, semantic networks, and decision trees. The expert system consists of a knowledge bank and an inference engine to infer or reason knowledge from stored knowledge banks. Expert systems are used centrally for human experts who need to deal with specific problems.
Learning Bank
The rule-based expert system captures expert knowledge in specific areas in a regular manner. These rules form a knowledge base, and then stop the evaluation of facts through inference engines to deal with specific issues. Example of rules:
If the sky is clear and the sun is gorgeous,
Then raincoats are not needed.
advantage
Because the rules are expressed in natural speech, it is easy to capture knowledge of the knowledge bank.
defect
Experts have different views on the same topic, which makes it difficult to control the category of knowledge.
Maintaining and updating the rules is a long process.
And there are different types of expert systems in different categories, such as rule-based expert systems, vague expert systems, and framework-based expert systems.
reasoning
Reasoning in the expert system is stopped by a forward or backward link. Forward linking is a data-driven inference technique that knows the beginning of data and proceeds according to that rule. Backlinking is a purpose-driven reasoning that starts from one end and pushes backwards to find data that supports the purpose.
Neural Networks
Artificial Neural Network (ANN) has been inspired by the human nervous system. The system works in exactly the same way as the human brain stores and disposes of knowledge. A neural network that is very similar to the human brain consists of a set of highly connected neurons or nodes. Information is stored, processed, and dissected in the network's neurons. Each node or neuron can activate other neurons in the network. The link or cohesion between neurons is called weight. A network can contain n neurons or nodes, which can make the network very complicated. A simple neural network consists of an input and output layer.
The following are different types of neural networks:
Feedforward neural network;
Convolutional Neural Network (CNN);
Recurrent neural network;
Long Term Memory Network (LSTM).
Artificial neural networks can learn by adjusting weights. It is this ability of neural networks that makes them suitable for machine learning. Different types of learning algorithms can be used for neural networks, the most prominent being the back propagation algorithm.
1. After understanding and writing natural speech and people;
2. Learning representation (know how to present knowledge to users);
3. Learning reasoning (knowing how to infer answers from stored knowledge to answer humans);
4. Machine learning inferred form and adapt to the new environment.
In short, AI is the study of rules and algorithms that help to build smart machines. The set of issues handled by AI is NP-complete.
Artificial intelligence is a universal research area that touches on five important disciplines:
1. Expert system;
2. Neural network;
Vague system
4. Robots;
5. Natural speech treatment.
Machine Learning (ML)
Machine learning is a subset of artificial intelligence. It learns data from an algorithm and obtains some data that humans require. Learning can turn people into geniuses and allow them to adapt to the new environment. Similarly, machine learning can make it strong enough to adapt to the new environment. The purpose of any machine learning algorithm is to maximize its purpose through the learning process so that it can dispose of invisible data.
The two key learning methods (algorithms) that complete machine learning are:
1. Monitor learning: External designer or logo data helps machine learning.
2. No monitoring learning: There is no tag data or external designer when learning the machine.
The purpose of artificial intelligence is to make the machine as intelligent as humans.
expert system
Expert systems are systems that rely on knowledge banks to deal with problems. The knowledge base can be represented in different ways, such as rules, semantic networks, and decision trees. The expert system consists of a knowledge bank and an inference engine to infer or reason knowledge from stored knowledge banks. Expert systems are used centrally for human experts who need to deal with specific problems.
Learning Bank
The rule-based expert system captures expert knowledge in specific areas in a regular manner. These rules form a knowledge base, and then stop the evaluation of facts through inference engines to deal with specific issues. Example of rules:
If the sky is clear and the sun is gorgeous,
Then raincoats are not needed.
advantage
Because the rules are expressed in natural speech, it is easy to capture knowledge of the knowledge bank.
defect
Experts have different views on the same topic, which makes it difficult to control the category of knowledge.
Maintaining and updating the rules is a long process.
And there are different types of expert systems in different categories, such as rule-based expert systems, vague expert systems, and framework-based expert systems.
reasoning
Reasoning in the expert system is stopped by a forward or backward link. Forward linking is a data-driven inference technique that knows the beginning of data and proceeds according to that rule. Backlinking is a purpose-driven reasoning that starts from one end and pushes backwards to find data that supports the purpose.
Neural Networks
Artificial Neural Network (ANN) has been inspired by the human nervous system. The system works in exactly the same way as the human brain stores and disposes of knowledge. A neural network that is very similar to the human brain consists of a set of highly connected neurons or nodes. Information is stored, processed, and dissected in the network's neurons. Each node or neuron can activate other neurons in the network. The link or cohesion between neurons is called weight. A network can contain n neurons or nodes, which can make the network very complicated. A simple neural network consists of an input and output layer.
The following are different types of neural networks:
Feedforward neural network;
Convolutional Neural Network (CNN);
Recurrent neural network;
Long Term Memory Network (LSTM).
Artificial neural networks can learn by adjusting weights. It is this ability of neural networks that makes them suitable for machine learning. Different types of learning algorithms can be used for neural networks, the most prominent being the back propagation algorithm.