Module 9

Question 1

Define:

Hybrid Intelligent System

Answer 1

A system that combines at least two intelligent technologies.

Question 2

Define:

Soft Computing

Answer 2

An emerging approach to building hybrid intelligent systems capable of reasoning and learning in an uncertain and imprecise environment.

Question 3

Define:

Black-box

Answer 3

A system where knowledge is lost on discretization.

Question 4

Define:

Neural Expert System

Connectionist Expert System

Answer 4

A hybrid system that combines a neural network and rule-based expert system.

Question 5

Describe:

Approximate Reasoning

with regards to inference machines.

Answer 5

Inference requires precise matching but a neural network allows for imprecise matching.

Question 6

Define:

Neuro-Fuzzy System

Answer 6

A hybrid system that combines a neural networks and fuzzy logic.

Question 7

Relate the neural layers to the fuzzy inference in a neuro-fuzzy system.

Answer 7

1. Input Layer
2. Fuzzification Layer
3. Fuzzy Rule Layer
4. Output Membership Layer
5. Defuzzification Layer

Question 8

Define:

Evolutionary Neural Networks

Answer 8

A hybrid system that combines neural networks and genetic algorithms.

Question 9

What makes a Evolutionary Neural Network strong?

Answer 9

The genetic algorithm attempts to find a set of weights (of the neural network) that minimizes the sum of squared errors.