Hallmark idea exchange=Knowledge community
Creates innovation and sharing.
Non-Social.
Online.
Community(external or internal)+Conent+Culture=Innovation/Sharing
Thursday, March 26, 2009
Tuesday, March 17, 2009
ANN vs. ES
ANN (artificial neural network)-An artificial neural network (ANN), often just called a "neural network" (NN), is a mathematical model or computational model based on biological neural networks. It consists of an interconnected group of artificial neurons and processes information using a connections approach to computation. In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase. In more practical terms neural networks are non-linear statistical data modeling tools. They can be used to model complex relationships between inputs and outputs or to find patterns in data.
ES (expert system)- Software that solves complex problems on behalf of the expert. An expert system is software that attempts to reproduce the performance of one or more human experts, most commonly in a specific problem domain, and is a traditional application and/or sub field of artificial intelligence.
Similarity: 1. Allow you to use technology to solve repetitive problems over and over.
2. Efficient, so much data and transactions to keep track of with business management software.
3. Must be both effective and efficient.
4. Both are used to solve nonlinear problems. Very complex problems.
5. Both are domain specific. They are both designed for specific problems. Related to a specific domain.
6. Must both be maintained and updated to keep useful. Must both be modified by removing and deleting certain content because knowledge is constantly being updated. Both must be evolving to accommodate new challenges to stay useful for along time
.7. Human intervention is still required.
8. Both are good knowledge management system and can be integrated into a website to make it more user friendly, powerful, and interactive.
Differences:
1. ES use "if, then" they can be opened up and you can see what is contained in the knowledge base. Implicit knowledge that is represented. You can see the reasons why the system thought through the problem and solve it.
2. ANN is not human readable. This network can perform meaningful solutions but it doesn't tell you what kind of logic is applied in this process.
3. NN are based mostly on numbers. ES are based mostly on classifications.
4. With an ES you need an expert to make the rules. With an ANN you don't depend so much on the expert. ANN is easier to develop because of this.
5. ANN is more computing intensive. ES is expressed without as much CPU power as the NN.
ES (expert system)- Software that solves complex problems on behalf of the expert. An expert system is software that attempts to reproduce the performance of one or more human experts, most commonly in a specific problem domain, and is a traditional application and/or sub field of artificial intelligence.
Similarity: 1. Allow you to use technology to solve repetitive problems over and over.
2. Efficient, so much data and transactions to keep track of with business management software.
3. Must be both effective and efficient.
4. Both are used to solve nonlinear problems. Very complex problems.
5. Both are domain specific. They are both designed for specific problems. Related to a specific domain.
6. Must both be maintained and updated to keep useful. Must both be modified by removing and deleting certain content because knowledge is constantly being updated. Both must be evolving to accommodate new challenges to stay useful for along time
.7. Human intervention is still required.
8. Both are good knowledge management system and can be integrated into a website to make it more user friendly, powerful, and interactive.
Differences:
1. ES use "if, then" they can be opened up and you can see what is contained in the knowledge base. Implicit knowledge that is represented. You can see the reasons why the system thought through the problem and solve it.
2. ANN is not human readable. This network can perform meaningful solutions but it doesn't tell you what kind of logic is applied in this process.
3. NN are based mostly on numbers. ES are based mostly on classifications.
4. With an ES you need an expert to make the rules. With an ANN you don't depend so much on the expert. ANN is easier to develop because of this.
5. ANN is more computing intensive. ES is expressed without as much CPU power as the NN.
Subscribe to:
Posts (Atom)