Architecture (Несколько текстов для зачёта), страница 4

Government agencies have Web sites where they post regulations, procedures, newsletters, and tax forms. Many elected officials—including almost all members of the United States Congress—have Web sites, where they express their views, list their achievements, and invite input from the voters. The Web also contains directories of e-mail and postal mail addresses and phone numbers.

Many merchants and publishers now do business on the Web. Web users can shop at Web sites of major bookstores, clothing sellers, and other retailers. Many major newspapers have special Web editions that are issued even more frequently than daily. The major broadcast networks use the Web to provide supplementary materials for radio and television shows, especially documentaries. Electronic journals in almost every scholarly field are now on the Web. Most museums now offer the Web user a virtual tour of their exhibits and holdings. These businesses and institutions usually use their Web sites to complement the non-Web parts of the operations. Some receive extra revenues from selling advertising space on their Web sites. Some businesses, especially publishers, provide limited information to ordinary Web users, but offer much more to users who buy a subscription.

The World Wide Web was developed by British physicist and computer scientist Timothy Berners-Lee as a project within the European Organization for Nuclear Research (CERN) in Geneva, Switzerland. Berners-Lee first began working with hypertext in the early 1980s. His implementation of the Web became operational at CERN in 1989, and it quickly spread to universities in the rest of the world through the high-energy physics community of scholars. Groups at the National Center for Supercomputing Applications at the University of Illinois in Champaign-Urbana also researched and developed Web technology. They developed the first major browser, named Mosaic, in 1993. Mosaic was the first browser to come in several different versions, each of which was designed to run on a different operating system. Operating systems are the basic software that control computers.

The architecture of the Web is amazingly straightforward. For the user, the Web is attractive to use because it is built upon a graphical user interface (GUI), a method of displaying information and controls with pictures. The Web also works on diverse types of computing equipment because it is made up of a small set of programs. This small set makes it relatively simple for programmers to write software that can translate information on the Web into a form that corresponds to a particular operating system. The Web’s methods of storing information associatively, retrieving documents with hypertext links, and naming Web sites with URLs make it a smooth extension of the rest of the Internet. This allows easy access to information between different parts of the Internet.

People continue to extend and improve on World Wide Web technology. Computer scientists predict that users will likely see at least five new ways in which the Web has been extended: new ways of searching the Web, new ways of restricting access to intellectual property, more integration of entire databases into the Web, more access to software libraries, and more and more electronic commerce.

HTML will probably continue to go through new forms with extended capabilities for formatting Web pages. Other complementary programming and coding systems such as Visual Basic scripting, Virtual Reality Markup Language (VMRL), Active X programming, and Java scripting will probably continue to gain larger roles in the Web. This will result in more powerful Web pages, capable of bringing information to users in more engaging and exciting ways.

On the hardware side, faster connections to the Web will allow users to download more information, making it practical to include more information and more complicated multimedia elements on each Web page. Software, telephone, and cable companies are planning partnerships that will allow information from the Web to travel into homes along improved telephone lines and coaxial cable such as that used for cable television. New kinds of computers, specifically designed for use with the Web, may become increasingly popular. These computers are less expensive than ordinary computers because they have fewer features, retaining only those required by the Web. Some computers even use ordinary television sets, instead of special computer monitors, to display content from the Web.

Neural Network

Neural Network, in computer science, highly interconnected network of information-processing elements that mimics the connectivity and functioning of the human brain. Neural networks address problems that are often difficult for traditional computers to solve, such as speech and pattern recognition. They also provide some insight into the way the human brain works. One of the most significant strengths of neural networks is their ability to learn from a limited set of examples.

Neural networks were initially studied by computer and cognitive scientists in the late 1950s and early 1960s in an attempt to model sensory perception in biological organisms. Neural networks have been applied to many problems since they were first introduced, including pattern recognition, handwritten character recognition, speech recognition, financial and economic modeling, and next-generation computing models.

Artificial Neural Network

The neural networks that are increasingly being used in computing mimic those found in the nervous systems of vertebrates. The main characteristic of a biological neural network, top, is that each neuron, or nerve cell, receives signals from many other neurons through its branching dendrites. The neuron produces an output signal that depends on the values of all the input signals and passes this output on to many other neurons along a branching fiber called an axon. In an artificial neural network, bottom, input signals, such as signals from a television camera’s image, fall on a layer of input nodes, or computing units. Each of these nodes is linked to several other “hidden’ nodes between the input and output nodes of the network. There may be several layers of hidden nodes, though for simplicity only one is shown here. Each hidden node performs a calculation on the signals reaching it and sends a corresponding output signal to other nodes. The final output is a highly processed version of the input.

Neural networks fall into two categories: artificial neural networks and biological neural networks. Artificial neural networks are modeled on the structure and functioning of biological neural networks. The most familiar biological neural network is the human brain. The human brain is composed of approximately 100 billion nerve cells called neurons that are massively interconnected. Typical neurons in the human brain are connected to on the order of 10,000 other neurons, with some types of neurons having more than 200,000 connections. The extensive number of neurons and their high degree of interconnectedness are part of the reason that the brains of living creatures are capable of making a vast number of calculations in a short amount of time.

Biological neurons have a fairly simple large-scale structure, although their operation and small-scale structure is immensely complex. Neurons have three main parts: a central cell body, called the soma, and two different types of branched, treelike structures that extend from the soma, called dendrites and axons. Information from other neurons, in the form of electrical impulses, enters the dendrites at connection points called synapses. The information flows from the dendrites to the soma, where it is processed. The output signal, a train of impulses, is then sent down the axon to the synapses of other neurons.

Artificial neurons, like their biological counterparts, have simple structures and are designed to mimic the function of biological neurons. The main body of an artificial neuron is called a node or unit. Artificial neurons may be physically connected to one another by wires that mimic the connections between biological neurons, if, for instance, the neurons are simple integrated circuits. However, neural networks are usually simulated on traditional computers, in which case the connections between processing nodes are not physical but are instead virtual.

Artificial neurons may be either discrete or continuous. Discrete neurons send an output signal of 1 if the sum of received signals is above a certain critical value called a threshold value, otherwise they send an output signal of 0. Continuous neurons are not restricted to sending output values of only 1s and 0s; instead they send an output value between 1 and 0 depending on the total amount of input that they receive—the stronger the received signal, the stronger the signal sent out from the node and vice-versa. Continuous neurons are the most commonly used in actual artificial neural networks.

The architecture of a neural network is the specific arrangement and connections of the neurons that make up the network. One of the most common neural network architectures has three layers. The first layer is called the input layer and is the only layer exposed to external signals. The input layer transmits signals to the neurons in the next layer, which is called a hidden layer. The hidden layer extracts relevant features or patterns from the received signals. Those features or patterns that are considered important are then directed to the output layer, the final layer of the network. Sophisticated neural networks may have several hidden layers, feedback loops, and time-delay elements, which are designed to make the network as efficient as possible in discriminating relevant features or patterns from the input layer.

Neural networks differ greatly from traditional computers (for example personal computers, workstations, mainframes) in both form and function. While neural networks use a large number of simple processors to do their calculations, traditional computers generally use one or a few extremely complex processing units. Neural networks also do not have a centrally located memory, nor are they programmed with a sequence of instructions, as are all traditional computers.

 The information processing of a neural network is distributed throughout the network in the form of its processors and connections, while the memory is distributed in the form of the weights given to the various connections. The distribution of both processing capability and memory means that damage to part of the network does not necessarily result in processing dysfunction or information loss. This ability of neural networks to withstand limited damage and continue to function well is one of their greatest strengths.

Neural networks also differ greatly from traditional computers in the way they are programmed. Rather than using programs that are written as a series of instructions, as do all traditional computers, neural networks are “taught” with a limited set of training examples. The network is then able to “learn” from the initial examples to respond to information sets that it has never encountered before. The resulting values of the connection weights can be thought of as a ‘program’.

Neural networks are usually simulated on traditional computers. The advantage of this approach is that computers can easily be reprogrammed to change the architecture or learning rule of the simulated neural network. Since the computation in a neural network is massively parallel, the processing speed of a simulated neural network can be increased by using massively parallel computers—computers that link together hundreds or thousands of CPUs in parallel to achieve very high processing speeds.

In all biological neural networks the connections between particular dendrites and axons may be reinforced or discouraged. For example, connections may become reinforced as more signals are sent down them, and may be discouraged when signals are infrequently sent down them. The reinforcement of certain neural pathways, or dendrite-axon connections, results in a higher likelihood that a signal will be transmitted along that path, further reinforcing the pathway. Paths between neurons that are rarely used slowly atrophy, or decay, making it less likely that signals will be transmitted along them.