Neural Network Concept in Artificial Intelligence
Abstract
Since the 1980's there have been renewed research efforts dedicated to neural networks. The present interest is largely due to the difficult problems confronted by artificial intelligence, and due to the deeper understanding of how the brain works, the recent developments in theoretical models, technologies and algorithms. One motivation of neural network research is the desire to build a new breed of powerful computers to solve a variety of problems that have proved to be very difficult with conventional computers. Another motivation is the desire to develop cognitive models that can serve as an alternative way to artificial intelligence. Human brain functions have not yet been successfully simulated in an AI system. Some existing neural network, on the other hand, have shown potential for these abilities. Using self-organization capabilities, neural networks are able to acquire and organize knowledge through learning in response to external stimuli. This paper addresses many techniques used in neural networks and possible applications in artificial intelligence. Some generic information about hybrid intelligent systems is also provided.
Introduction
There have been a variety of neural network models developed by researchers of different backgrounds, from different point of view and with different aims and applications. However, neural networks are emulation of biological neural systems. With such an emulation it is hoped that some brain abilities, such as generalization, and attention focusing, can be simulated. The neural network can be defined in many ways. From the structural point of view, a neural network can be defined as a directed network (or graph) with ...
... middle of paper ...
...ithms can be integrated with neural networks to solve the complex problems in machine learning, such systems are called hybrid intelligent systems. Neural networks are very powerful tools for Intelligence Systems. Although there are some limitations in terms of the complexity of the neural circuit and the lack of representation in very complex systems, there is an ongoing research to improve performance and capabilities of neural networks.
Bibliography
1. Braspenning P.J. and Thuijsmann F. (1991) Artificial Neural Networks
2. Kamp Y. and Hasler M. (1990) Recursive Neural Networks for Associative Memory
3. Wu Jian-Kang (1994) Neural Networks and Simulation Methods
4. Medsker L.R. (1995) Hybrid Intelligent Systems
5. Parberry Ian (1994) Circuit Complexity and Neural Networks
6. Neural Networks
7. Boltzmann Model
8. Kohonen Model
In an article I read written on July 13, 2014 by Ken Bain “Flummoxed by Failure-or Focused?” he discussed how there are two types of students the “helpless” student who think they aren 't smart enough and the “mastery” or “growth” students who will try everything before they cave in and how students the “hopeless” students think their intelligence is fixed. Also in an interview with Ken Bain conducted by the Project Information Literacy on October 10, 2012 , Mr. Bain discussed more of his view on learning like that you don 't learn from your experiences, but about thinking about your experience which is a process he called “deep learning”. He also discusses issues with strategic learner who basically only perform for the high grade and don 't ask questions after they get their answer. Many students have this notion that learning is all about getting a high grade and once they have it they are done, But if they do it just for the grade it can cause some serious problems, they won’t learn how to deep learn, and it can maybe affect their career.
The advent of neural net with the seminal work of Hopfield , popularized the use of machine intelligence techniques in the pattern recognition. However, the dense and inherent structure of neural networks is not suitable for VLSI implementation. So, researchers in the neural network domain tried to simplify the structure of the neural network by pruning unnecessary connections. Simultaneously, the CA research community explored the advantages of the sparse network structure of cellular automata for relevant applications. The hybridization of cellularity and neural network has given rise to the popular concept of cellular neural networks.
Kandel, E. R., J. H. Schwarz, and T. M. Jessel. Principles of Neural Science. 3rd ed. Elsevier. New York: 1991.
Soldiers sown from dragon teeth, golden robots built by Hephaestus, and three-legged tables that could move under their own power - the Greeks were the first to cross the divide between machine and human. Although the history of Artificial Intelligence (AI) began with these myths and speculations, it is becoming a part of everyday life. How did it evolve so quickly, and what are its implications for the future?
Stergiou, C., & Siganos, D. (2011, August 6). Neural Networks. Retrieved August 6, 2011, from
Artificial intelligence has come a long way since the first robot. In 1950, Alan Turing of Britain publishes, Computer Machinery and Intelligence. This book was proposed to be the birth of artificial intelligence as we know it. The first robot that presents the usage of artificial intelligence was built in 1969. The purpose of this robot was to try out navigation using basic tools such as cameras and bump sensors (Marshall 371). Since then, we have made a million robots way better than this one and we’re going to continue doing so. While the world advances, so is technology. It’s slowly progressing and become better and more reliable. Artificial intelligence is a certain type of technology that is resourceful to our nation. We are using it in the medical field, it’s been helpful to military forces, and it’s helping our world become a better place.
As our research into science and technology ever increases its seems inevitable that in the near future Artificial Intelligent machines will exist and become part of our everyday life such as we see with modern computers today.
There are problems that are computationally hard i.e. ... ... middle of paper ... ..., which are discussed in detail in [5]. 1.3.3 Training and Performance The training of the network can be carried out using the backpropagation algorithm.
The traditional notion that seeks to compare human minds, with all its intricacies and biochemical functions, to that of artificially programmed digital computers, is self-defeating and it should be discredited in dialogs regarding the theory of artificial intelligence. This traditional notion is akin to comparing, in crude terms, cars and aeroplanes or ice cream and cream cheese. Human mental states are caused by various behaviours of elements in the brain, and these behaviours in are adjudged by the biochemical composition of our brains, which are responsible for our thoughts and functions. When we discuss mental states of systems it is important to distinguish between human brains and that of any natural or artificial organisms which is said to have central processing systems (i.e. brains of chimpanzees, microchips etc.). Although various similarities may exist between those systems in terms of functions and behaviourism, the intrinsic intentionality within those systems differ extensively. Although it may not be possible to prove that whether or not mental states exist at all in systems other than our own, in this paper I will strive to present arguments that a machine that computes and responds to inputs does indeed have a state of mind, but one that does not necessarily result in a form of mentality. This paper will discuss how the states and intentionality of digital computers are different from the states of human brains and yet they are indeed states of a mind resulting from various functions in their central processing systems.
Gonzales, M. E. Q. Neural networks and Mental Representation: An essay on Harmony and Rationality. In: Trans/ Form/Ação, São Paulo, v. 14, p.93-108, 1991.
Neuro – Linguistic programming is concerned with how individuals absorb and make sense of information (Young 1983, p.1012). It is referred to as a model of human behaviour and cognition (weaver 2010 p.40). It has been stated (O’Connor, 2001, p1) as the study of brilliance and quality. Neuro-linguistic programming started with John Grinder, who was a linguistic professor and Richard Bandlar who had both a mathematical and computer programming background (Gleeson, 2009, p.6). Both professors had an interest in modelling patterns of behaviour to produce excellence. The traditional focus of neuro-linguisitc programming was with therapeutic techniques however, it has now steered in many other directions (Gleeson, 2009, p.6). Neuro-linguisitc programming cannot be pinned down to one definition (O’Connor, 2001, p1). Although it has tried to be defined on many occasions, each definition focuses on different aspects of it (Dimmick, 1995, pxi). The co-founders have defined neuro-linguisitc programming themselves; however their definitions seem to differ (Dimmick, 1995, pxi). Bandlar defines it as a methodology of modelling which leaves behind a trail of techniques (Dimmick, 1995, pxi). Grinder defines it an epistemology which is the study of self creation or how knowledge is obtained (Dimmick, 1995, pxi). Neuro-linguisitc programming is found within a variety of practices with a range of practitioners utilizing these skills. (McDermott, Jago 2001, p.1). This paper will look at the benefits of neuro-linguisitc programming and will conclude with how this would benefit social work practitioners.
Artificial neural networks are systems implemented on computer systems as specialized hardware or sophisticated software that loosely model the learning and remembering functions of the human brain. They are an attempt to simulate the multiple layers of processing elements in the brain, called neurons. These elements are implemented in such a way so that the layers can learn from prior experience and remember their outputs. In this way, the system can learn to recognize certain patterns and situations and apply these to certain priorities and output appropriate results. These types of neural networks can be used in many important situations such as priority in an emergency room, for financial assistance, and any type of pattern recognition such as handwritten or text-to-speech recognition.
Artificial Intelligence is the scientific theory to advance the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines. This is going to hold the key in the future. It has always fa...
Singh, Y. & Chauhan, A. (2009). Neural networks in data mining. Journal of Theoretical and
Machine learning systems can be categorized according to many different criteria. We will discuss three criteria: Classification on the basis of the underlying learning strategies used, Classification on the basis of the representation of knowledge or skill acquired by the learner and Classification in terms of the application domain of the performance system for which knowledge is acquired.