translate:
Summary of advanced applications of neural network and artificial intelligence
This paper is a comprehensive article, which introduces the concepts and application of artificial intelligence and neural network.This article was originally selected because the neural network was learned in the process of learning machine learning, because the artificial neural network is closer to the human brain in terms of its principles and functional characteristics. It is not a given program that performs operations step by step, but is able to adapt itself to the environment, summarize the rules, perform some operation, recognition or process control. I think there must be many important applications in artificial intelligence, so I chose this article.
The article is a comprehensive article that introduces the concepts and applications of artificial intelligence and neural networks.The artificial neural network is closer to the human brain in terms of its constitution principle and functional characteristics.It is not a given program that performs operations step by step,but can adapt itself to the environment and summarize the rules.Perform an operation, recognition.,or process control.
The first part mainly introduces artificial intelligence.
Artificial intelligence is defined as an artificial object, such as a computer or machine, that shows intelligent behavior capable of dealing with complex problems. And what is intelligence? This involves issues such as consciousness, self, thinking, and so on, and the only intelligence we know is human intelligence.It is a kind of ability to imagine and create memory understanding, pattern recognition, choice, adapt to change and experience learning. The main purpose of artificial intelligence is to make machines behave more like humans, and secondly, to make machines more like humans in the way they solve complex problems but consume less time than humans. Today, artificial intelligence is divided into two parts: strong ai and weak ai.Strong ai means that machines can think on their own, like the scenes in the movies, and even replace humans.The weak ai is the performance of machines that seem to have intelligence, such as playing chess apps, and all the steps it makes to play chess are stored in a computer in advance. The chess app itself doesn't think or plan. How do you know if the machine has intelligent behavior? In 1950, Alan Turing put forward the Turing test, and there is not much explanation for Turing test, because the teacher introduced it in class.
For the origin of artificial intelligence, it is associated with many disciplines, especially philosophy, logic, mathematics, computing, psychology/cognitive science, biological science/neuroscience.
The second part mainly introduces artificial neural network.This section also introduces three small parts, introducing the concept of artificial neural network,the types of neural network learning methods and an important function in artificial neural network-Artificial incentive function.
The first part introduces the concept of artificial neural network. An artificial neural network is a network of processors (neurons) connected, each with a portion of the local storage space (very small).These neurons operate only their own local data and input data (which are entered in one way through links and circuits), and each neuron uses a rule to know the input signal. Output these signals to other neurons, and this calculation of the output data is called an incentive function.
The structure of the neural network generally has three layers, as shown below. The first layer is the input layer, which is used to interact directly with the outside world, and the second layer is the hidden element, which is used to complete the calculation according to the required function. The third layer is the output layer.
The second part of neural network learning can be divided into three types: supervised learning, unsupervised learning and strengthened learning. In supervisory learning, each instance consists of an input object and an expected output value.Therefore, errors and differences between the expected and actual results of each node on the output layer can be found, which will be used to determine the weight of the network node (according to
the learning rules). That is, the expected output value on each node is determined by an external teacher.
There are no external teachers in unsupervised learning, so the way of learning is based on clustering, and according to input, the model set is divided into different classes. This kind of learning model can also be called self-organizing mode, typical example is the hebbian learning law and the competition learning law, and unsupervised learning is more important than supervised learning. Because the brain is usually unsupervised.
Strengthening learning is based on unsupervised learning and supervised learning, and in the process of exploration, by exploring the unknown environment while building an environmental model and learning an optimal strategy, Each action corresponds to a reward, and finally gets the greatest reward for data processing.
The third part introduces three kinds of incentive functions. The first threshold function, when the total input is less than the threshold, sets 0, and when the total input value is greater than the threshold, sets 1.
The second is a segmented linear function that can take values between 0,1, depending on the magnification of the linear operation of a region.
The third is the sigmoid function, which can use a range between 0 and 1, but can sometimes take a range from 1 to 1, An example of a sigmoid function is a hyperbolic tangent.
The third part mainly introduces several advanced applications of neural network.
The first application is the computer interface of the human brain based on neural network. The computer interface of human brain is one of the most promising interface technologies between human and machine.BCI is also called the Siwei interface. It is actually a communication channel between the brain and the computer, which allows the signals sent by the brain to interact directly with external activities, such as controlling a cursor, Or the user can enter a phone number by gazing at the keyboard of a display.The interface provides a means of communication between the brain and the interface it wants to control, and the BCI interface makes it possible for a paralyzed person to write a book or control an electric wheelchair. Eg is the best choice to implement BCI, but brainwaves are very weak and there are many kinds of noise.
A signal is obtained from the human brain, then processed, extracted from the features, then classified, and then fed back to the human through the application interface. The number and speed of BCI research has been growing rapidly over the past five years, with no more than six groups studying it in 1995, and at least 20 groups studying BCI now.
The second application is to understand and describe applications in object behavior. Trajectory analysis is one of the core problems in behavior understanding. Trajectory pattern learning can be used to detect anomalies and to predict object trajectory. A model that learns the semantic region by analyzing the trajectory of a moving object in a scene or framework. The first path is encoded to indicate the location of the image and its instantaneous speed.Then the clustering algorithm is applied to classify the tracks according to different spatial and velocity distributions, and in each cluster, the space of the tracks is close and the speed is similar. This class can represent a mode of activity. Based on this orbital cluster,the statistical model of semantic regions in the scene can be obtained by estimating the density and velocity distribution of each activity pattern.The model is based on the combination of vector quantization neural network and neuron types with short-term memory ability. The resulting pedestrian trajectory model will be used to evaluate the new trajectory, predict the future trajectory of the object, randomly generate new trajectory.
The third application is artificial neural network in computer graphics.
Artificial neural network has played a very important role in the image field. The image designer is trying to combine the actual image with the computer generated image to enhance the visualization of the output object. Using thermal sensing technology can produce some of the most authentic images.
The fourth application is automatic walking robot and underwater robot.
Automatic walking robot is based on the modular concept. The problem of making an automatic walking robot can be disassembled into several functional problems. Breaking down a complex problem into simple, manageable little problems, and the research in this field combines knowledge of biology, mechanics, and information technology, Then develop a dynamic, stable, mobile vehicle using neural network control.The same is true of underwater robots, and underwater machines help salvage operations, prevent pollution, rescue at sea and marine scientific research. So underwater robots have developed a lot over the years.
The fifth application is facial animation.
Face modeling and animation is one of the most difficult tasks in computer graphics, and it is very difficult to turn life into digital form. Use layered b-surface as a base to create facial animation. Neural networks can be used to learn the features of every face expression in an animation sequence.
The sixth is the neural network to strengthen anti-virus technology.
Artificial neural networks and artificial intelligence play an increasingly important role in virus detection, which strengthens the internal functions of anti-virus technology, allowing it to detect and repair all kinds of viruses. For example, IBM's neural network startup detection technology provides additional security by imitating human neurons to learn the difference between infected and uninfected records.Many examples of viruses and non-viruses show that neural networks perform better than traditional hand-adjusted wizard searches for viruses.
The fourth part mainly introduces the application of artificial intelligence.
The first application is data mining and knowledge extraction. Three basic techniques in artificial intelligence are applied, including knowledge expression, and data mining wants to discover patterns of interest from large amounts of data, which can be used in many forms, such as association rules. Decision rules and decision trees.There is also knowledge acquisition and knowledge reasoning, and the pattern found from the data set needs to be verified in different applications.
The second application is the artificial system. The expert system is a subset of artificial intelligence, and the expert system is an artificial intelligence program, which has expert knowledge in specific fields and knows how to use its knowledge to correctly respond to related problems.
The third application is nature and original process NLP. Natural language processing is a subdomain of artificial intelligence. Its goal is to achieve a human-like language processing mechanism. The following picture is a model of NLP.
The fourth application is cyanology. Robotics is part of the field of artificial intelligence.
The fifth application is to apply artificial intelligence to the game. Modern games usually use 3D animation graphics to give people a real feeling. Artificial intelligence in most computer games is not an academic artificial intelligence, but a very close to artificial intelligence technology, which creates an intellectual illusion.Game artificial intelligence includes techniques that combine programming and design practices: path search, neural networks, emotional models, social scenes, finite state machines, rule systems, Decision tree learning and other techniques.
At the end of the paper, some of the problems that researchers are working on are, for example, whether machines are aware of their existence? What does it mean to humans? Will neural networks be completely similar to the human brain and so on.At the end of the paper, some of the problems that researchers are working on are, for example, whether machines are aware of their existence? What does it mean to humans? Will neural networks be completely similar to the human brain and so on.
The subject of this paper is finished. Through the study and reading of this paper, it is found that the computer world can benefit a lot from the neural network method. In the future, artificial intelligence will develop machines and computers that are more complex than we are today, and they may really have simple common sense and have similar human intelligence in some fields. The future development of artificial intelligence may really change our world.
The original title is "Review of Advanced Applications of Neural Networks and Artificial Intelligence" report
original:
"Review of Advanced Applications of Neural Networks and Artificial Intelligence" report
This paper as a whole is a review article, introducing some concepts of artificial intelligence and neural networks and some areas of application. I chose this article because I learned about neural networks in the process of learning machine learning, because artificial neural networks are closer to the human brain in terms of composition principles and functional characteristics. It is not a given program that performs operations step by step, but It is the ability to adapt to the environment, summarize rules, complete certain calculations, identify or process control, and feel that there must be many important applications in artificial intelligence, so I chose this article.
The article is divided into six parts. The first and second parts mainly introduce the concepts of artificial intelligence and artificial neural networks, as well as some related reserve knowledge in machine learning. The third chapter discusses the application of neural networks, the fourth chapter discusses the application of artificial intelligence, the fifth chapter is the conclusion, and the sixth chapter presents future problems to be solved.
The first part mainly introduces artificial intelligence.
Artificial intelligence is defined as a man-made object (such as a computer or machine) that exhibits intelligent behavior capable of handling complex problems. And what is intelligence? This involves issues such as consciousness, ego, thinking, etc. The only intelligence we understand is the intelligence of human beings. It is an ability to imagine, create, remember, understand, recognize, select, adapt to change, and learn from experience. The main purpose of artificial intelligence is to make machines behave more like humans, and secondly, to make machines more similar to humans in solving complex problems but consume less time than humans. Artificial intelligence research has been divided into two parts: strong AI and weak AI . Strong AI means that machines can think autonomously, like the scenes played in movies, and even replace humans. The weak AI is the performance of the machine. They seem to have intelligence, such as some chess applications, and all the chess steps it makes are pre-stored in the computer by people. The chess application itself does not think or plan. . And how to know whether the machine has intelligent behavior? In 1950 , Alan Turing proposed the Turing test. I will not explain the Turing test here because the teacher introduced it in class.
For the origin of artificial intelligence, it is linked to many disciplines, especially philosophy, logic, mathematics, computing, psychology / cognitive science, biological sciences / neuroscience.
The second part mainly introduces artificial neural network. This part mainly introduces three small parts, including the concept of artificial neural network, the types of learning methods of neural network, and an important function artificial excitation function in artificial neural network.
An artificial neural network is a network composed of many processors (neurons) connected, and each neuron has a part of the local storage space (small). These neurons only operate on their own local data and input data (one-way input through links and lines). Each neuron uses certain rules to learn about the input signal and output these signals to other neurons. A calculation rule for the output data is called the excitation function.
The structure of the neural network generally has three layers, as shown in the figure below, the first layer is the input layer, which is used to directly interact with the outside world, and the second layer is the hidden element, which is used to complete the calculation according to the required function. The third layer is the output layer.
The second small part of neural network learning methods can be divided into three types: supervised learning, unsupervised learning and reinforcement learning. In supervised learning, each instance consists of an input object and a desired output value. Therefore, errors and discrepancies between the expected and actual results of each node on the output layer can be found, and they will be used to determine the changes in the weights of the network nodes (according to the learning rules). That is, the expected output value on each node is determined by an external teacher.
There is no external teacher in unsupervised learning, so this learning method is based on clustering. According to the input, the model set will be divided into different classes. This learning mode can also be called self-organizing mode. Typical examples are the Hebbian learning rule and the competitive learning rule. Unsupervised learning is more important than supervised learning because the brain usually performs unsupervised learning.
Reinforcement learning is based on unsupervised learning and supervised learning. By exploring the unknown environment while building an environment model and learning an optimal strategy, in the process of exploration, each action corresponds to a reward, and finally a reward is obtained. Data processing in the most rewarding way.
The third subsection introduces three excitation functions. The first threshold function is set to 0 when the total input value is less than the threshold value, and set to 1 when the total input value is greater than the threshold value .
The second is a piecewise linear function, which can take values between 0 and 1 , depending on the magnification factor of the linear operation in a certain area.
The third is the sigmoid function. This function can use the range between 0 and 1 , but sometimes it can also take the range of -1 to 1. An example of the sigmoid function is the hyperbolic tangent function.
The third part mainly introduces several advanced applications of neural network.
The first application is the human-brain-computer interface based on neural networks. Human-brain-computer interface is one of the very promising interface technologies between humans and machines. BCI is also known as the Thinking Machine Interface. It is essentially a communication channel between the brain and a computer, enabling signals from the brain to interact directly with external activities, such as controlling a cursor, or a user can enter a string of phone numbers by gazing at the keyboard of a monitor. The interface provides a communication pathway between the brain and the interface it wants to control. The BCI interface makes it possible for a paralyzed person to write a book or control an electric wheelchair. EEG is the best option to achieve BCI , however brain waves are very weak and there are many kinds of noise. Therefore, it is very important to select what kind of features are useful, how to extract useful features, and how to suppress noise. Neural networks can be used to distinguish noisy signals from sensitive ones, improving the accuracy of conscious task classification. The following is a simple schematic diagram of a BCI .
The signal is first obtained from the human brain, and then processed to extract features, then classify, and finally give feedback to people through the application interface. The number and speed of BCI research has grown rapidly over the past five years . In 1995 there were no more than 6 groups working on it, and now there are at least 20 groups working on BCI .
The second application is in understanding and describing the behavior of objects. Trajectory analysis is one of the core problems in behavior understanding problems. Trajectory pattern learning can be used to detect anomalies and can also be used to predict object trajectories. Models of semantic regions are learned by analyzing the trajectories of moving objects in a scene or frame. First, the trajectories are encoded to represent the position of the image and its instantaneous velocity. A clustering algorithm is then applied to classify the trajectories according to different spatial and velocity distributions. Within each cluster, the trajectories are close in space and similar in velocity, and this class can represent an activity pattern. Based on this cluster of trajectories, by estimating the density and velocity distributions of each activity pattern, a statistical model over the semantic regions in the scene can be derived. The model is based on a combination of neural networks implementing vector quantization and neuron types with short-term memory capabilities, using hierarchical self-organizing neural networks to learn and identify distribution patterns of trajectories. The generated pedestrian trajectory models are used to evaluate new trajectories, predict the future trajectories of objects, and randomly generate new trajectories.
A third application is artificial neural networks in computer graphics
Artificial neural networks have played an important role in the image field. Graphic designers are trying to combine actual images with computer-generated images to enhance the visualization of output objects. Some of the most realistic images are produced using thermal sensing technology.
The fourth application is autonomous walking robot & underwater robot.
The basis of autonomous walking robots is the modular concept. The problem of making an autonomous walking robot can be broken down into sets of functional problems. Decompose a complex problem into simple and tractable small problems. Research in this field combines the relevant knowledge of biology, mechanics and information technology to develop a dynamic stable mobile means of transportation. The same is true of underwater robots, and underwater machines help in salvage operations, pollution prevention, marine rescue and marine scientific expeditions, and more. Therefore, underwater robots have been greatly developed in recent years.
The fifth application is facial animation
Face modeling and animation is one of the most difficult tasks in computer graphics today, and translating life into digital form is very difficult. Use layered B- surfaces as the base layer to create facial animations. Neural networks can be used to learn the characteristics of each facial expression in an animation sequence.
The sixth is neural network to strengthen anti-virus technology
Artificial neural networks and artificial intelligence are playing an increasingly important role in virus detection, strengthening the internal capabilities of antivirus technology, allowing it to detect and repair all types of viruses. For example, IBM 's neural network priming detection technology provides additional security by mimicking human neurons to learn the difference between infected and uninfected recordings. Numerous viral and non-viral examples show that neural network learning methods perform better at identifying viruses than traditional hand-tuned variation-level mage searches.
The fourth part mainly introduces the application of artificial intelligence.
The first application is data mining and knowledge extraction. Three basic techniques in artificial intelligence are applied including knowledge representation, and data mining to discover patterns of interest from large amounts of data. These patterns can take many forms, such as association rules, decision rules, and decision trees. There are also knowledge acquisition and knowledge reasoning. The patterns found from the data set need to be verified in different applications, so the deduction of mining results is a necessary technology for data mining applications.
The second application is artificial systems. An expert system is a subset of artificial intelligence, and an expert system is an artificial intelligence program that has expert-level knowledge of a specific domain and knows how to use its knowledge to properly respond to relevant questions.
The third application is natural and raw processing NLP . Natural language processing is a subfield of artificial intelligence. Its goal is to achieve human-like language processing mechanisms. The following figure is the model of NLP .
The fourth application is robotics. Robotics is part of the field of artificial intelligence.
The fifth application is the application of artificial intelligence to games. Modern games often use 3D animated graphics to give a realistic feel. The artificial intelligence in most computer games is not academic artificial intelligence, but a technology very close to artificial intelligence, which creates an illusion of intelligence. Game AI includes techniques that combine programming and design practices: path finding, neural networks, emotional models, social scenarios, finite state machines, rule systems, decision tree learning, and a few others.
The article concludes with questions that some researchers are addressing: For example, can machines be aware of their own existence? What does it mean for humans? Will the neural network be exactly similar to the human brain and so on. I think the only certainty is that artificial intelligence is developing at a very fast speed. While it brings us surprises and conveniences, it may also have some drawbacks that are slowly revealed. It requires the joint efforts of human beings to develop it and control it.
The main body of this dissertation is completed. Through the study and reading of this paper, I found that the computer world can actually benefit a lot from neural network methods. In the future, artificial intelligence will develop machines and computers that are more complex than we have today, and they may indeed have simple common sense and human-like intelligence in some professional fields. The development of artificial intelligence in the future may really make our world look new.
Note: Many thanks to the author of this article, it has benefited me a lot.