Matja Gams

1

COMPUTER MODELS OF THE MIND

• Matja Gams
• Jozef Stefan Institute,
• Ljubljana University
• Slovenia

2
Models of the Mind

• neural networks
• evolutionary algorithms
• symbolic learning
• intelligent agents

3
Truly intelligent?
4
Neural networks

• artificial networks uniform simple filters!
• 30 types of neurons, different structures,
  unique
• constantly changing and adapting to environment

5
How smart is a neuron?

• cant draw it well why?
• a simple switch McCulloch and Pitt 1943
• a neuron is a computer Hodgkin, Huxley 1952
• can a simple model represent the most complex
  system in our universe?

6
(No Transcript)
7

• Weak intelligence through the principle and
  paradox of multiple knowledge

 M. Gams Weak intelligence Through the
principle and paradox of multiple knowledge,
Advances in computation Theory and practice,
Volume 6, Nova science publishers, inc., NY, ISBN
1-56072-898-1, pp. 245, 2001. Weak intelligence -
Why computers will never think (unless designed
differently)? It is claimed that the major
thinking power comes from interactions between
multiple subprocesses. The principle of "multiple
knowledge", in a way similar to the Heisenberg
principle, is introduced to divide nonintelligent
and intelligent thinking).
8

• Weak intelligence through the principle and
  paradox of multiple knowledge

8 CONSEQUENCES 8.1 Occam's Razor Vs. Multiple
Knowledge 8.2 Bayes' Classifier And Multiple
Knowledge 8.3 Properties of Knowledge 9
MANY-WORLDS THEORY AND QUANTUM COMPUTING 9.1
Paradoxes of Modern Physics 9.2 Interpretations
of Quantum Physics 9.3 The Many-Worlds Theory 9.4
Objections to the Many-Worlds Interpretation 9.4
Quantum Computing 9.5 From Many Worlds to the
Principle of Multiple Knowledge 10 STRONG AI
FIGHTS BACK 11 CONCLUSION
9
Moravec
10
Weak AI - Qualitative Leaps
11
Discussion

• Improving models of the mind
• What is missing?
• Information society - first SW generation with
  some degree of freedom when executing tasks
  observes environment, communicates with several
  actors such as other computers, people etc.
• First true assistants, not just slaves
• We need them and they need us
• New (weak) AI comprehensions needed

12

• TRUE (NEW)
• INTELLIGENCE, CONSCIOUSNESS

In around 30-50 years How? Easy question design
it. Hard question explain it maybe
impossible.