РефератыИностранный языкCoComputer History Essay Research Paper ABSTRACTCurrent neural

Computer History Essay Research Paper ABSTRACTCurrent neural

Computer History Essay, Research Paper


ABSTRACT


Current neural network technology is the most progressive of the artificial intelligence


systems today. Applications of neural networks have made the transition from laboratory


curiosities to large, successful commercial applications. To enhance the security of automated


financial transactions, current technologies in both speech recognition and handwriting


recognition are likely ready for mass integration into financial institutions.


RESEARCH PROJECT


TABLE OF CONTENTS


Introduction 1


Purpose 1


Source of Information 1


Authorization 1


Overview 2


The First Steps 3


Computer-Synthesized Senses 4


Visual Recognition 4


Current Research 5


Computer-Aided Voice Recognition 6


Current Applications 7


Optical Character Recognition 8


Conclusion 9


Recommendations 10


Bibiography 11


INTRODUCTION


? Purpose


The purpose of this study is to determine additional areas where artificial intelligence


technology may be applied for positive identifications of individuals during financial


transactions, such as automated banking transactions, telephone transactions , and home


banking activities. This study focuses on academic research in neural network technology .


This study was funded by the Banking Commission in its effort to deter fraud.


Overview


Recently, the thrust of studies into practical applications for artificial intelligence


have focused on exploiting the expectations of both expert systems and neural network


computers. In the artificial intelligence community, the proponents of expert systems


have approached the challenge of simulating intelligence differently than their counterpart


proponents of neural networks. Expert systems contain the coded knowledge of a human expert


in a field; this knowledge takes the form of “if-then” rules. The problem with this approach


is that people don?t always know why they do what they do. And even when they can express this


knowledge, it is not easily translated into usable computer code. Also, expert systems are


usually bound by a rigid set of inflexible rules which do not change with experience gained


by trail and error. In contrast, neural networks are designed around the structure of a


biological model of the brain. Neural networks are composed of simple components called


“neurons” each having simple tasks, and simultaneously communicating with each other by


complex interconnections. As Herb Brody states, “Neural networks do not require an explicit


set of rules. The network – rather like a child – makes up its own rules that match the


data it receives to the result it?s told is correct” (42). Impossible to achieve in expert


systems, this ability to learn by example is the characteristic of neural networks that makes


them best suited to simulate human behavior. Computer scientists have exploited this system


characteristic to achieve breakthroughs in computer vision, speech recognition, and optical


character recognition. Figure 1 illustrates the knowledge structures of neural networks


as compared to expert systems and standard computer programs. Neural networks restructure


their knowledge base at each step in the learning process.


This paper focuses on neural network technologies which have the potential to increase security


for financial transactions. Much of the technology is currently in the research phase and has


yet to produce a commercially available product, such as visual recognition applications.


Other applications are a multimillion dollar industry and the products are well known, like


Sprint Telephone?s voice activated telephone calling system. In the Sprint system the neural


network positively recognizes the caller?s voice, thereby authorizing activation of his


calling account.


The First Steps


The study of the brain was once limited to the study of living tissue. Any attempts at an


electronic simulation were brushed aside by the neurobiologist community as abstract conceptions


that bore little relationship to reality. This was partially due to the over-excitement in


the 1950?s and 1960?s for networks that could recognize some patterns, but were limited in


their learning abilities because of hardware limitations. In the 1990’s computer simulations


of brain functions are gaining respect as the simulations increase their abilities to predict


the behavior of the nervous system. This respect is illustrated by the fact that many


neurobiologists are increasingly moving toward neural network type simulations. One such


neurobiologist, Sejnowski, introduced a three-layer net which has made some excellent predictions


about how biological systems behave. Figure 2 illustrates this network consisting of three


layers, in which a middle layer of units connects the input and output layers. When the network


is given an input, it sends signals through the middle layer which checks for correct output.


An algorithm used in the middle layer reduces errors by strengthening or weakening connections


in the network. This system, in which the system learns to adapt to the changing conditions,


is called back-propagation. The value of Sejnowski’s network is illustrated by an experiment


by Richard Andersen at the Massachusetts Institute of Technology. Andersen?s team spent years


researching the neurons monkeys use to locate an object in space (Dreyfus and Dreyfus 42-61).


Anderson decided to use a neural network to replicate the findings from their research. They


“trained” the neural network to locate objects by retina and eye position, then observed


the middle layer to see how it responded to the input. The result was nearly identical to what


they found in their experiments with monkeys.


Computer-Synthesized Senses


? Visual Recognition


The ability of a computer to distinguish one customer from another is not yet a reality. But, recent breakthroughs in neural network visual technology are


bringing us closer to the time when computers will positively identify a person.


? Current Research


Studying the retina of the eye is the focus of research by two professors at the California


Institute of Technology, Misha A. Mahowald and Carver Mead. Their objective is to electronically


mimic the function of the retina of the human eye. Previous research in this field consisted


of processing the absolute value of the illumination at each point on an object, and required


a very powerful computer.(Thompson 249-250). The analysis required measurements be taken over


a massive number of sample locations on the object, and so, it required the computing power of a


massive digital computer to analyze the data.


The professors believe that to replicate the function of the human retina they can use a neural


network modeled with a similar biological structure of the eye, rather than simply using massive


computer power. Their chip utilizes an analog computer which is less powerful than the previous


digital computers. They compensated for the reduced computing power by employing a far more


sophisticated neural network to interpret the signals from the electronic eye. They modeled the


network in their silicon chip based on the top three layers of the retina which are the best


understood portions of the eye.(250) These are the photoreceptors, horizontal cells, and bipolar cells.


The electronic photoreceptors, which make up the first layer, are like the rod and cone cells in the eye.


Their job is to accept incoming light and transform it into electrical signals. In the second


layer, horizontal cells use a neural network technique by interconnecting the horizontal cells


and the bipolar cells of the third layer. The connected cells then evaluate the estimated


reliability of the other cells and give a weighted average of the potentials of the cells


around it. Nearby cells are given the most weight and far cells less weight.(251)


This technique is very important to this process because of the dynamic nature of image


processing. If the image is accepted without testing its probable accuracy, the likelihood


of image distortion would increase as the image changed.


The silicon chip that the two professors developed contains about 2,500 pixels? photoreceptors


and their associated image-processing circuitry. The chip has circuitry that allows a professor


to focus on each pixel individually or to observe the whole scene on a monitor. The professors


stated in their paper, “The behavior of the adaptive retina is remarkably similar to that of


biological systems” (qtd in Thompon 251).


The retina was first tested by changing the light intensity of just one single pixel while the


intensity of the surrounding cells was kept at a constant level. The design of the neural network


caused the response of the surrounding pixels to react in the same manner as in biological retinas.


They state that, “In digital systems, data and computational operations must be converted into


binary code, a process that requires about 10,000 digital voltage changes per operation.


Analog devices carry out the same operation in one step and so decrease the power consumption


of silicon circuits by a factor of about 10,000″ (qtd in Thompson 251).


Besides validating their neural network, the accuracy of this silicon chip displays the usefulness


of analog computing despi

te the assumption that only digital computing can provide the accuracy


necessary for the processing of information.


As close as these systems come to imitating their biological counterparts, they still have a long


way to go. For a computer to identify more complex shapes, e. g., a person?s face, the professors


estimate the requirement would be at least 100 times more pixels as well as additional circuits


that mimic the movement-sensitive and edge-enhancing functions of the eye. They feel it is possible


to achieve this number of pixels in the near future. When it does arrive, the new technology will


likely be capable of recognizing human faces.


Visual recognition would have an undeniable effect on reducing crime in automated financial transactions.


Future technology breakthroughs will bring visual recognition closer to the recognition of individuals,


thereby enhancing the security of automated financial transactions.


? Computer-Aided Voice Recognition


Voice recognition is another area that has been the subject of neural network research.


Researchers have long been interested in developing an accurate computer-based system capable


of understanding human speech as well as accurately identifying one speaker from another.


? Current Research


Ben Yuhas, a computer engineer at John Hopkins University, has developed a promising system for


understanding speech and identifying voices that utilizes the power of neural networks. Previous attempts


at this task have yielded systems that are capable of recognizing up to 10,000 words, but only when each


word is spoken slowly in an otherwise silent setting. This type of system is easily confused by back


ground noise (Moyne 100).


Ben Yuhas’ theory is based on the notion that understanding human speech is aided, to some small degree,


by reading lips while trying to listen. The emphasis on lip reading is thought to increase as the


surrounding noise levels increase. This theory has been applied to speech recognition by adding a


system that allows the computer to view the speaker?s lips through a video analysis system while


hearing the speech.


The computer, through the neural network, can learn from its mistakes through a training session. Looking


at silent video stills of people saying each individual vowel, the network developed a series of


images of the different mouth, lip, teeth, and tongue positions. It then compared the video images


with the possible sound frequencies and guessed which combination was best.


Yuhas then combined the video recognition with the speech recognition systems and input a video frame


along with speech that had background noise. The system then estimated the possible sound frequencies


from the video and combined the estimates with the actual sound signals. After about 500 trial runs the


system was as proficient as a human looking at the same video sequences.


This combination of speech recognition and video imaging substantially increases the security factor by


not only recognizing a large vocabulary, but also by identifying the individual customer using the system.


? Current Applications


Laboratory advances like Ben Yuhas? have already created a steadily increasing market in speech recognition.


Speech recognition products are expected to break the billion-dollar sales mark this year for the first time.


Only three years ago, speech recognition products sold less than $200 million (Shaffer, 238).


Systems currently on the market include voice-activated dialing for cellular phones, made secure by their


recognition and authorization of a single approved caller. International telephone companies such as Sprint


are using similar voice recognition systems. Integrated Speech Solution in Massachusetts is investigating


speech applications which can take orders for mutual funds prospectuses and account activities (239).


? Optical Character Recognition


Another potential area for transaction security is in the identification of handwriting by optical


character recognition systems (OCR). In conventional OCR systems the program matches each letter in a


scanned document with a pre-arranged template stored in memory. Most OCR systems are designed specifically


for reading forms which are produced for that purpose. Other systems can achieve good results with


machine printed text in almost all font styles. However, none of the systems is capable of recognizing


handwritten characters. This is because every person writes differently.


Nestor, a company based in Providence, Rhode Island has developed handwriting recognition products based


on developments in neural network computers. Their system, NestorReader, recognizes handwritten characters


by extracting data sets, or feature vectors, from each character. The system processes the input


representations using a collection of three by three pixel edge templates (Pennisi, 23). The system then


lays a grid over the pixel array and pieces it together to form a letter. Then the network discovers


which letter the feature vector most closely matched. The system can learn through trial and error,


and it has an accuracy of about 80 percent. Eventually this system will be able to evaluate all symbols


with equal accuracy.


It is possible to implement new neural-network based OCR systems into standard large optical systems.


Those older systems, used for automated processing of forms and documents, are limited to reading typed


block letters. When added to these systems, neural networks improve accuracy of reading not only typed


letters but also handwritten characters. Along with automated form processing, neural networks will


analyze signatures for possible forgeries.


Conclusion


Neural networks are still considered emerging technology and have a long way to go toward achieving their


goals. This is certainly true for financial transaction security. But with the current capabilities,


neural networks can certainly assist humans in complex tasks where large amounts of data need to be analyzed.


For visual recognition of individual customers, neural networks are still in the simple pattern matching


stages and will need more development before commercially acceptable products are available. Speech


recognition, on the other hand, is already a huge industry with customers ranging from individual computer


users to international telephone companies. For security, voice recognition could be an added link to the


chain of pre-established systems. For example, automated account inquiry, by telephone, is a popular method


for customers to determine the status of existing accounts. With voice identification of customers, an


option could be added for a customer to request account transactions and payments to other institutions.


For credit card fraud detection, banks have relied on computers to identify suspicious transactions.


In fraud detection, these programs look for sudden changes in spending patterns such as large cash withdrawals


or erratic spending. The drawback to this approach is that there are more accounts flagged for possible


fraud than there are investigators. The number of flags could be dramatically reduced with optical character


recognition to help focus investigative efforts.


It is expected that the upcoming neural network chips and add-on boards from Intel will add blinding speed


to the current network software. These systems will even further reduce losses due to fraud by enabling


more data to be processed more quickly and with greater accuracy.


Recommendations


Breakthroughs in neural network technology have already created many new applications in financial transaction


security. Currently, neural network applications focus on processing data such as loan applications, and


flagging possible loan risks. As computer hardware speed increases and as neural networks get smarter,


“real-time” neural network applications should become a reality. “Real-time” processing means the network


processes the transactions as they occur.


In the mean time,


1. Watch for advances in visual recognition hardware / neural networks. When available, commercially produced


visual recognition systems will greatly enhance the security of automated financial transactions.


2. Computer aided voice recognition is already a reality. This technology should be implemented in automated


telephone account inquiries. The feasibility of adding phone transactions should also be considered.


Cooperation among financial institutions could result in secure transfers of funds between banks when


ordered by the customers over the telephone.


3. Handwriting recognition by OCR systems should be combined with existing check processing systems.


These systems can reject checks that are possible forgeries. Investigators could follow-up on the


OCR rejection by making appropriate inquiries with the check writer.


Winston, Patrick. Artificial Intelligence. Menlo Park: Addison-Wesley Publishing, 1988.


Welstead, Stephen. Neural Network and Fuzzy Logic in C/C++. New York: Welstead, 1994.


Brody, Herb. “Computers That Learn by Doing.” Technology Review August 1990: 42-49.


Thompson, William. “Overturning the Category Bucket.” BYTE January 1991: 249-50+.


Hinton, Geoffrey. “How Neural Networks Learn from Experience.” Scientific American September 1992: 145-151.


Dreyfus, Hubert., and Stuart E. Dreyfus. “Why Computers May Never Think Like People.” Technology Review January 1986: 42-61.


Shaffer, Richard. “Computers with Ears.” FORBES September 1994: 238-239.


————————————————————–

Сохранить в соц. сетях:
Обсуждение:
comments powered by Disqus

Название реферата: Computer History Essay Research Paper ABSTRACTCurrent neural

Слов:3030
Символов:21888
Размер:42.75 Кб.