Objective and Strategy
1. Historical background
From AI to AGI
AGI differs from mainstream AI in the following points:
- Stressing on the general-purpose nature of intelligence,
- Taking a holistic or integrative viewpoint on intelligence,
- Believing the possibility of an AI that is comparable to human intelligence in the near future.
Of course, AGI and mainstream AI have overlaps in many places.
2. Research objective
In the field of AI/AGI, there are different research objectives, corresponding to different understandings (working definitions) of intelligence, in terms of where the similarity between the brain and the computer should be expected:
- [Structure]
Rationale: Intelligence is produced by the human brain.
Background: Neuroscience, biology, etc.
Examples: SyNAPSE, HTM
Challenge: There may be biological details that are neither possible nor necessary to be reproduced in AI systems.
- [Behavior]
Rationale: Intelligence is displayed in how the human beings behave.
Background: Psychology, linguistics, etc.
Examples: Turing Test, cognitive modeling
Challenge: There may be psychological details that are neither possible nor necessary to be reproduced in AI systems.
- [Capability]
Rationale: Intelligence is evaluated by the practical problems solved.
Background: Computer application guided by domain knowledge
Examples: Deep Blue, expert system
Challenge: There is no defining problem, and the special-purpose solutions lack generality and flexibility.
- [Function]
Rationale: Intelligence is a collection of cognitive processes.
Background: Computer science
Examples: Mainstream AI textbooks, Soar, LIDA
Challenge: The AI techniques developed so far are highly fragmented and rigid.
- [Principle]
Rationale: Intelligence is a form of rationality or optimality.
Background: Logic, mathematics, etc.
Examples: AIXI, NARS
Challenge: There are too many things to be explained by a simple theory.
Reason for the diversity: human intelligence is described at a certain level of abstraction (the science aspect of AI), and then the description is used as the objective to be achieved (the engineering aspect of AI).
The above objectives are related, but still very different, and do not subsume each other. The preferred way to achieve one is not preferred for the others.
Common mistakes:
- There is one "true" or "natural" understanding of intelligence, and the others are simply wrong.
- The different understandings of intelligence are complementary, so should be considered altogether in an AGI project.
- The different understandings of intelligence are different paths toward the same goal.
References:
3. Overall strategy
On one hand, the ultimate goal of AI is to reproduce intelligence as a whole, while on the other hand, engineering practice must be step-by-step. There are three overall strategies:
- [Hybrid]
Approach: To develop individual functions first (using different theories and techniques), then to connect them together.
Argument: (AA)AI: More than the Sum of Its Parts, Ronald Brachman
Difficulty: Compatibility of the theories and techniques
- [Integrated]
Approach: To design an architecture first, then to design its modules (using various techniques) accordingly.
Argument: Cognitive Synergy: A Universal Principle for Feasible General Intelligence?, Ben Goertzel
Difficulty: Isolation, specification, and coordination of the functions
- [Unified]
Approach: Using a single technique to start from a core system, then to extend and augment it incrementally.
Argument: Toward a Unified Artificial Intelligence, Pei Wang
Difficulty: Extendability of the core technique
The selection of strategy partially depends on the selection of the objective.
4. Prospects
This course is organized according to the following assumption: "Intelligence" mainly corresponds to certain rational principle abstracted from the human mental mechanism, and this principle is not followed by the conventional computer systems. The best way to reproduce this principle in AI systems is to depend on a unified core technique, and to incrementally specify and implement it.
Reading
- Non-Axiomatic Logic: A Model of Intelligent Reasoning, Sec. 1.1
- Rigid Flexibility: The Logic of Intelligence, Ch. 1