Learning Curve…

MB0047 : a. Bring out the relationship between AI and Neural Network. b. what is the difference between DSS and ES?

Posted on: September 30, 2011

MB0047 : a. Bring out the relationship between AI and Neural Network.
 b. what is the difference between DSS and ES?

      Answer: – Artificial Intelligence and Neural Networks

Artificial intelligence is a field of science and technology based on disciplines such as computer science, biology, psychology, linguistics, mathematics and engineering. The goal of AI is to develop computers that can simulate the ability to think, see, hear, walk, talk and feel. In other words, simulation of computer functions normally associated with human intelligence, such as reasoning, learning and problem solving.

Neural network software can learn by processing sample problems and their solutions. As neural nets start to recognize patterns, they can begin to program themselves to solve such problems on their own.

Neural networks are computing systems modeled after the human brain’s mesh like network of interconnected processing elements, called neurons. The human brain is estimated to have over 100 billion neuron brain cells. The neural networks are lot simpler in architecture. Like the brain, the interconnected processors in a neural network operate in parallel and interact dynamically with each other.

This enables the network to operate and learn from the data it processes, similar to the human brain. That is, it learns to recognize patterns and relationships in the data. The more data examples it receives as input, the better it can learn to duplicate the results of the examples it processes. Thus, the neural networks will change the strengths of the interconnections between the processing elements in response to changing patterns in the data it receives and results that occur.

For example, neural network can be trained to learn which credit characteristics result in good or bad loans. The neural network would continue to be trained until it demonstrated a high degree of accuracy in correctly duplicating the results of recent cases. At that point it would be trained enough to begin making credit evaluations of its own.

A neural network is designed to simulate a set of neurons, usually connected by synapses. Each neuron makes a simple decision based on its other input synapses, and places the decision on its output synapses. This model mimics the behavior of a brain, and is considered vital to create a true learning system, though modern computers (barring super-computers) do not have the computational resources to execute a neural network with a sufficient number of nodes to be useful (you would need at least a few million neurons firing in unison to be useful).
Artificial intelligence, of course, is software that is designed to pretend like it’s a living, thinking creature. Older implementations were not learning systems, but rather would take input and offer a conditioned response provided by the programmer ahead of time. These systems seemed to be highly intelligent, so long as you did not leave its realm of preplanned responses. Newer AI systems learn by interacting with the user (for example, remembering their favorite color or music artist), and can sometimes even figure out correlated data based on this information.

However, current AI systems tend to still have limited spheres of knowledge, and without external learning sources, cannot make any intelligent responses or decisions outside this realm of information. The missing component, of course, is a system that is capable of learning information and incorporating what it learns into its current knowledge base. Neural networks hold the promise of bridging this gap in the “learning curve” that AI systems have by allowing the AI to actually learn topics that were not covered during its original “training” or “programming.”

The relationship between these two technologies could be said to be symbiotic in nature; both of these can be implemented without the other (i.e. a NN could be used inside a coffee maker for some advanced coffee-making logic, and an AI can certainly use other sources of information to make valid responses), but the combination of the two would allow for a more realistic AI that would be capable of learning data by making correlations between seemingly unrelated data (which is how humans learn, coincidentally).

Different between expert system and decision support system

  1. DSS aid in problem solving by allowing for manipulation of data & models whereas ES allow experts to ‘teach’ computers about their field so that the system may support more of the decision making process for less expert decision makers.
  2. DSS most often contain equations that the system uses to solve problems or update reports immediately, and the users makes the final decisions on the basis of the information whereas an expert system works from a much larger set of modeling rules, uses concepts from AI to process and store the knowledge base & scans base to suggest a final decision through inference.
  3. DSS only supports the decision making process & a human user is required to weigh all the factors in making a decision whereas ES must acquire knowledge from an expert and apply a large but standard set of probability based rules to make a decision in a specific problem setting.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

Learning days (Calendar)

September 2011
« Aug   Oct »

Knowledge Bank (Archives)

I am on Twitter

Blog Stats

  • 532,900 hits

Enter your email address to subscribe to this blog and receive notifications of new posts by email.

Join 43 other followers

%d bloggers like this: