Transcript presentation

Artificial Intelligence System
Designer 4GN
ISP RAS
Alexander Zhdanov
Artificial Intelligence
Problems solved by
means of AI systems:

Pattern recognition


Data mining
Image recognition
Automated reasoning
 Expert systems
 Prediction
 Automated control

Approaches used:
•Artificial Neural networks
•Fuzzy logic
•Reinforcement learning
•Stochastic approaches
•Structural representation
AAC Framework for AI system
design

Explicitly deals with
Well-suited for:
 Pattern recognition
Pattern recognition
 Knowledge base formation
systems
 Prediction
Expert systems
 Automated analysis
Data mining
 May be based on
system
 Determined chaos systems
Adaptive control
 3rd generation neural networks
systems
 Genetic algorithms


Stochastic methods
Open for other sophisticated
techniques
AAC Framework for AI system
design
AAC Comparison with other AI-approaches:

Artificial neural networks - perform only patter
recognition or approximation and demand a priori
learning. AAC systems have abilities for self-control
 Fuzzy logic systems – demand a priori formulated
fuzzy rules. AAC systems deduce rules themselves
and corrects them if necessary
AAC Framework for AI system
design
For example, the AdCAS system for car suspension
adaptive control could not be created simply on basis
of another method: artificial NN, reinforcement
learning, fuzzy logic or any another approach.
AAC Framework applicability
 Pattern
recognition systems
 Prediction, forecasting systems
 Expert systems, decision making
 Adaptive control systems
 Highly adjustable to problem domain or
context
Universality of a system
“Applicability of a method is inversely proportional to
its universality”
It is impossible to create
universal control
system for ANY
customers and ANY
problem, because its
parameters have to
depend on given
objects
• Parameters of CS, which are independent
from CO
1) The structure of the CS operation;
2) The ways in which the CS subsystems are constructed –
the recognition system, knowledge base and other
subsystems;
3) The models of the neuron-like elements of which the the
CS
subsystems are constructed; etc.
• Parameters of CS, which dependent from
CO
1) The input and output variables and their characteristics;
2) The rules of pattern formation which will be required
for the control;
3) The rules of knowledge formation in the knowledge
base
4) The qualitative criteria for the evaluation of the possible
states of the CS, for the control quality evaluation, for
the determination of the goal functions; etc.
Computer Aided System
Engineering

Pros






Produces highly customizable solutions
Ease of use: does not require hardcore
programming skills
Adaptability
Flexibility
Development of end-user solutions
Cons (requires from developers)



High level of abstraction on analysis stage
Deep understanding of system principia
Ability to translate abstraction into concrete
notions
CASE for design of AI systems
Computer model of given application
Model of sensors
AAC
method
Programming
Prototype
of CS
Model of CO
Model of actuators
The software Tools
Proposal #1: Development of
CASE for design of AI systems
based on AAC method
Main features:







Drastically reduces time and resources required for
development
Explicit AI orientation
Export/import interfaces with simulation software and
with hardware
Advanced visualization and analysis techniques
Easy to use for non-experienced programmer
Makes process of AI system design more transferable
Open interfaces
Three main phases of applied AI
systems projecting for various tasks
Control System
Phase I.
CS
Controlled Object
Sensors
CO
Actuators
Environment
The projection and development of the CS prototype and its testing
on program models of the CO, Sensors and Actuators. (1-2 years)

Phase II.
CS
Sensors
CO
Actuators
Environment
The debugging of the CS prototype on real CO, sensors, actuators or
their physical models.

Phase III.
CS
Sensors
CO
Actuators
Environment
Building-in of the CS into the real CO, where the CS is implemented
on real (on-board) processor.

Proposal #2: AAC-based
multiagent system architecture
Development of multiagent system architecture
based on AAC
Main features of such system:
•
•
•
•
•
•
•
•
Explicitly distributed
AI-based (in sense of AAC)
Self-monitoring, Self-adaptability, Self-manageability, Selflearning
Secure
Adaptable to heterogeneous environment
Decentralized control
Flexibility
Eco-system principles based
Thank you for your time
Welcome to discussion