1、附录二英文参考文献 原文 Artificial Neural Networks Artificial Neural Networks - Basic Features Composed of a large number of processing units connected by a nonlinear, adaptive information processing system. It is the basis for modern neuroscience research findings presented, trying to simulate a large neural
2、network processing, memory, information processing way of information. Artificial neural network has four basic characteristics: (1) non-linear non-linear relationship is the general characteristics of the natural world. The wisdom of the brain is a nonlinear phenomenon. Artificial neural activation
3、 or inhibition in two different states, this behavior mathematically expressed as a linear relationship. Threshold neurons have a network with better performance, can improve fault tolerance and storage capacity. (2) non-limitation of a neural network is usually more extensive neuronal connections m
4、ade. The overall behavior of a system depends not only on the characteristics of single neurons, and may primarily by interaction between units, connected by the decision. By a large number of connections between the cells of non-simulated brain limitations. Associative memory limitations of a typic
5、al example of non- (3) characterization of artificial neural network is adaptive, self-organizing, self-learning ability. Neural networks can not only deal with the changes of information, but also process information the same time, nonlinear dynamic system itself is also changing. Iterative process
6、 is frequently used in describing the evolution of dynamical systems. (4) Non-convexity of the direction of the evolution of a system, under certain conditions, will depend on a particular state function. Such as energy function, and its extreme value corresponding to the state of the system more st
7、able. Non-convexity of this function is more than one extremum, this system has multiple stable equilibrium, which will cause the system to the evolution of diversity. Artificial neural network, neural processing unit can be expressed in different objects, such as features, letters, concepts, or som
8、e interesting abstract patterns. The type of network processing unit is divided into three categories: input units, output units and hidden units. Input unit receiving the signal and data outside world； output unit for processing the results to achieve the output； hidden unit is in between the input
9、 and output units can not be observed from outside the system unit. Neurons and the connection weights reflect the strength of the connections between elements of information representation and processing reflected in the network processing unit connected relationships. Artificial neural network is
10、a non-procedural, adaptability, the brains information processing style, its essence is transformation through the network and dynamic behavior is a parallel distributed information processing, and to varying degrees and levels mimic brain information processing system. It is involved in neural scie
11、nce, thinking, science and artificial intelligence, computer science and other interdisciplinary fields. Artificial neural networks are parallel distributed systems, using traditional artificial intelligence and information processing technology is completely different mechanism to overcome the trad
12、itional symbol of artificial intelligence-based logic in dealing with intuition, unstructured information deficiencies, adaptive, Self-organization and the characteristics of real-time learning. Artificial Neural Network History In 1943, psychologist WSMcCulloch mathematical logician W. Pitts neural
13、 network and the establishment of a mathematical model, called the MP model. They put forward by MP model neurons and network structure of formal mathematical description of methods, that a single neuron can perform logic functions, thus creating the era of artificial neural network. In 1949, psycho
14、logists proposed the idea of synaptic strength variable. 60 years, artificial neural network to the further development of improved neural network models have been proposed, including the sensors and the adaptive linear element, etc. M. Minsky and so careful analysis of the sensor represented by the
15、 neural network system capabilities and limitations, the in 1969 published a Perceptron book, pointed out that the sensor can not solve the issue of higher order predicate. Their argument has greatly influenced research in neural networks, combined with serial computers and artificial intelligence a
16、t the achievements made to cover up the development of new computer and artificial intelligence, new ways of necessity and urgency to the research of artificial neural networks at a low ebb . In the meantime, some artificial neural network remains committed to the study, researchers proposed to adap
17、t resonance theory (ART Wang), Zi Zuzhiyingshe, Ren Zhi machine network, while for the neural network Shuxue research. More research and development of neural network research foundation. In 1982, California Institute of Technology physicist JJHopfield proposed Hopfield neural grid model, the concep
18、t of computational energy concept gives the network stability of the judge. In 1984, he made continuous time Hopfield neural network model for the neural computer research done pioneering work to create a neural network for associative memory and optimization of computing new ways to effectively pro
19、mote the study of neural networks, In 1985, there are scholars of the Boltzmann model, the use of statistical thermodynamics in the study simulated annealing technology to ensure the overall stability of the whole system tends to point. 1986 to study the microstructure of cognition, proposed the the
20、ory of parallel distributed processing. Artificial neural networks in various countries of the importance attached by the U.S. Congress passed a resolution to January 5, 1990 began with a decade as the brain decade, the international research organization called on its members to brain of the 10 in
21、to the global behavior. In Japans real-world computing (RWC) project, the artificial intelligence research has become an important part. The main consideration of artificial neural network model topology of the network connection, the characteristics of neurons, learning rules. Currently, nearly 40
22、kinds of neural network model, including back propagation network, perceptron, self organizing maps, Hopfield networks, Boltzmann machines, meet the resonance theory. According to the connection topology, neural network model can be divided into: (1) before the network to the network each neuron for
23、 the former level of input and output to the next level, network, no feedback, you can use a directed loop-free graph. This network signal from the input space and output space transform its information processing capabilities from a simple nonlinear function of several complex. Network structure is
24、 simple, easy to implement. Back-propagation network is a typical feedforward network. (2) feedback network network neurons have feedback, you can use an undirected complete graph. This neural network information processing is the state of transformation, you can deal with dynamic systems theory. St
25、ability of the system is closely related with the associative memory function. Hopfield networks, Boltzmann machines belong to this category. Neural network learning is an important part of its adaptability is achieved through learning. According to the environmental changes in the value of the righ
26、t to make adjustments to improve the systems behavior. Hebb proposed by the Hebb learning rule neural network learning algorithm for the foundation. Hebb learning rule that eventually occurred in the synapses between neurons, synaptic contacts with the synaptic strength of neuronal activity before a
27、nd after the change. On this basis, it proposed a variety of learning rules and algorithms to meet the needs of different network models. Effective learning algorithm, making neural network connection weights through the adjustment, construction of the objective world of the intrinsic representation
28、, forming a unique information processing method, information Cunchu and processing reflected in the network connection. According to different learning environment, neural network learning methods can be divided into supervised learning and unsupervised learning. In monitoring the study, the traini
29、ng sample data added to the network input side, while the corresponding desired output and network output compared Dedao error signal, thereby Kongzhiquanzhi connection strength adjustments, Jing Hou several training convergence to a determine the weights. When the sample situation changes, the weig
30、hts can be modified by learning to adapt to the new environment. Use supervised learning back propagation neural network model has the network, and HC. Non-supervised learning, the prior is not a given standard sample placed directly into the network environment, learning stage and become one session. At this point, learn
