home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!paladin.american.edu!darwin.sura.net!mips!sdd.hp.com!caen!nic.umass.edu!dime!rabbit.cs.umass.edu!connolly
- From: connolly@rabbit.cs.umass.edu (Christopher Ian Connolly)
- Newsgroups: comp.ai.neural-nets
- Subject: Re: Neural Nets and Brains
- Message-ID: <50961@dime.cs.umass.edu>
- Date: 27 Jul 92 21:20:17 GMT
- References: <BILL.92Jul23135614@ca3.nsma.arizona.edu> <arms.711935064@spedden> <BILL.92Jul23224539@ca3.nsma.arizona.edu>
- Sender: news@dime.cs.umass.edu
- Organization: University of Massachusetts, Amherst
- Lines: 21
-
- In article <BILL.92Jul23224539@ca3.nsma.arizona.edu> bill@nsma.arizona.edu (Bill Skaggs) writes:
- >Well, McCulloch and Pitts proved a long time ago that their networks
- >could emulate any Turing machine; it's hard to get any any stronger
- >than that.
-
- I know this is a nit as far as this thread goes, but I think it should
- be clarified:
-
- I don't recall McCulloch and Pitts proving Turing equivalence (this
- doesn't seem possible without a potentially infinite supply of units),
- but as I recall, Kleene proved that McCulloch-Pitts networks were
- essentially equivalent to finite state automata. If I remember
- correctly, this shows up in "Automata Studies", Shannon and McCarthy,
- eds., Princeton University Press, 1956.
-
- Is this what you were thinking of?
- --
- - - - - - - -
- Christopher Ian Connolly connolly@cs.umass.edu
- Laboratory for Perceptual Robotics wa2ifi
- University of Massachusetts at Amherst Amherst, MA 01003
-