Classifications [Frame-Based Expert Systems, Neural Network-Based Expert Systems, Neuro-Fuzzy Expert Systems]

Classifications [Frame-Based Expert Systems, Neural Network-Based Expert Systems, Neuro-Fuzzy Expert Systems]

This organize knowledge using frames, like objects in programming.

Frame-Based System

These ____ store attributes and values related to specific concepts, making them useful in natural language processing and other knowledge representation tasks.

frames

A _______ is a data structure with typical knowledge about a particular object or concept.

Frame

Frames, first proposed by?

Marvin Minsky, 1970s

Each frame has its own name and a set of ____ associated with it.

attributes

It provide a natural way for the structured and concise representation of knowledge.

Frames

This provides a means of organizing knowledge in slots to describe various attributes and characteristics of the object.

Frames

These are an application of object-oriented programming for expert system.

Frames

Frames are an application of ______ for expert system.

object-oriented programming

This is a programming method that uses objects as a basis for analysis, design and implementation.

Object-oriented programming

In object-oriented programming, an _______ is defined as a concept, abstraction or thing with crisp boundaries and meaning for the problem at hand.

object

TRUE OR FALSE

All objects have identity and are clearly distinguishable.

TRUE

A knowledge engineer refers to an object as a ______ (the term, which has become the AI jargon).

frame

The concept of this is defined by a collection of slots.

frame

The concept of a frame is defined by a collection of ______.

slots

Each _____ describes a particular attribute or operation of the frame.

slot

A slot may contain ?

• a default value

• a pointer to another frame

• a set of rules

• procedure by which the slot value is obtained.

ENUMERATE: Typical Information included in a Slot

• Frame

• Relationship of the frame to the other

• Slot

• Default slot value

• Range of the slot

• Procedural

A slot value can be ?

• symbolic

• numeric

• Boolean.

TRUE OR FALSE

Slot values can be assigned when the frame is created or during a session with the expert system.

TRUE

The ______ is taken to be true when no evidence to the contrary has been found.

default value

The _______ determines whether a particular object complies with the stereotype requirements defined by the frame.

range of the slot value

A slot can have a _______ attached to it, which is executed if the slot value is changed or needed.

procedure

Frame-based expert systems also provide an extension to the slot-value structure through the application of ______.

facets

A ______ is a means of providing extended knowledge about an attribute of a frame.

facet

These are used to establish the attribute value, control end-user queries, and tell the inference engine how to process the attributes.

Facets

The word frame often has a vague The frame may refer to a particular object, for example the computer IBM Aptiva S35, or to a group of similar objects. To be more precise, we will use the _______ when referring to a particular object, and the ______ when referring to a group of similar objects.

instance-frame

class-frame

A ______ describes a group of objects with common

class-frame

TRUE OR FALSE

Each frame “knows” its class.

TRUE

Integrate ________ to learn patterns from data

and improve decision-making.

artificial neural networks

These systems are widely used in applications like image

recognition and speech processing, where traditional rule-based

approaches might struggle.

Neural Network-Based Expert Systems

The ________ are a biologically inspired set of models that facilitate computers learning from observed data.

neural network or the artificial neural networks (ANN)

The brain has an estimated ______, each neuron has an average of _______ connections that directly link it to other neurons.

100 billion neurons

10 thousand

The most complex structure, natural or artificial, on earth

brain

An _________ is an information-processing system that adopts the neural structure of the human brain for analyzing data, finding patterns, classification, and prediction through a learning process using a series of mathematical equations.

artificial neural network (ANN)

They are capable of decision-making by using what they learn while encountering problems.

artificial neural network (ANN)

It referred to neural networks as a family of algorithms which has recently seen a revival under the name _______

“deep learning.”

A more advanced hybrid approach is _______, which merge the learning capabilities of neural networks. with the uncertainty-handling strengths of fuzzy logic.

Neuro-Fuzzy Expert Systems

These systems are particularly useful in financial forecasting and automated control systems, where both structured learning and flexible reasoning are necessary.

Neuro-Fuzzy Expert Systems

Modern neuro-fuzzy systems are usually represented as __________

special multilayer feedforward neural networks.

A ________ is based on a fuzzy system which is trained by a learning algorithm derived from neural network theory.

neuro-fuzzy system

A neuro-fuzzy system can be viewed as a 3-layer feedforward neural network. Describe each layer.

• The first layer represents input variables

• The middle (hidden) layer represents fuzzy rules

• The third layer represents output variables.

In neuro-fuzzy system, fuzzy sets are encoded as ?

(fuzzy) connection weights.

It is not necessary to represent a fuzzy system like this to apply a

learning algorithm to it. However, it represents the data flow of

input processing and learning within the model.

In neuro-fuzzy system, these are encoded as (fuzzy) connection weights.

fuzzy sets

TRUE OR FALSE

Sometimes a 5-layer architecture is used, where the fuzzy sets are represented in the units of the second and fifth layer.

FALSE

Sometimes a 5-layer architecture is used, where the fuzzy sets are represented in the units of the second and fourth layer.

TRUE OR FALSE

A neuro-fuzzy system can be always (i.e.\ before, during and after learning) interpreted as a system of fuzzy rules. It is also possible to create the system out of training data from scratch, as it is possible to initialize it by prior knowledge in form of fuzzy rules.

TRUE

TRUE OR FALSE

Not all neuro-fuzzy models specifiy learning procedures for fuzzy rule creation.

TRUE

TRUE OR FALSE

• The learning procedure of a neuro-fuzzy system takes the semantical properties of the underlying fuzzy system into account. This results in constraints on the possible modifications applicable to the system parameters.
  However, not all neuro-fuzzy approaches have this property.

TRUE

TRUE OR FALSE

• A neuro-fuzzy system approximates an $n$-dimensional (unknown) function that is partially defined by the training data. The fuzzy rules encoded within the system represent vague samples, and can be viewed as prototypes of the training data. A neuro-fuzzy system should not be seen as a kind of (fuzzy) expert system, and it has nothing to do with fuzzy logic in the narrow sense.

TRUE

The _________ are the basic motivation for the development of artificial neural networks.

biological neurons