Sunday, August 03, 2008

need to integrate different approaches to AI (Minsky)

Two different ways to represent an apple - a semantic network and a connectionist network

Minsky argues that to explain intelligence we need to integrate both of these approaches and not take an either / or attitude. The popularity of a connectionist only approach has retarded research into intelligence.

Connectionist networks (based on numbers showing strength of associations) can learn to recognise many important types of patterns - without any need for a person to program them. But number based networks have limitations. Every relationship is reduced to a number or strength so there remains almost no trace of the evidence that led to it, eg. the number 12 could represent all sorts of things

I see the popularity (of Connectionist Networks), in recent years, as having retarded the search for higher level ideas about human psychological machinery ... research on commonsense thinking kept advancing until about 1980, but then it was clearly recognised that further progress would need ways to acquire and organise millions of fragments of commonsense knowledge. That prospect seemed so daunting that most researchers decided to try, instead, to invent machines that could learn, by themselves, all the knowledge that they would need - in short, to invent new kinds of "baby machines" ...

Quite a few of these learning machines did indeed learn to do some useful things, but none of them went on to develop higher-level reflective Ways to Think - and I suspect that this was mainly because they tried to represent knowledge in numerical terms....

... I do not mean to suggest that such networks are not important ... it seems safe to assume that many of the low level processes in our brains must use some form of Connectionist Networks
- Minsky, pp. 289-91, The Emotion Machine
This helps me situate the work of Rodney Brooks (behavioural AI) as important but limited.

Logical vs.Analogical or Symbolic vs. Connectionist or Neat vs. Scruffy - this paper by Minsky (1990) has more detail

update: I'm still summarising minsky's book on the learning evolves wiki minsky page

No comments: