home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!mcsun!uknet!strath-cs!robert@cs.strath.ac.uk
- From: robert@cs.strath.ac.uk (Robert B Lambert)
- Newsgroups: comp.ai.neural-nets
- Subject: Correctness of NNs
- Message-ID: <10088@baird.cs.strath.ac.uk>
- Date: 24 Jul 92 15:47:11 GMT
- Sender: robert@cs.strath.ac.uk
- Organization: Comp. Sci. Dept., Strathclyde Univ., Glasgow, Scotland.
- Lines: 56
-
- This query is directed to Prof. Armstrong, although I would be interested in
- opinions in general.
-
- Coming from a vision background, I was puzzled after reading Prof. Armstrong's
- posting on the reliability of neural networks. Surely to be able to state that
- network X is 100% reliable, the entire input set must be known. From experience,
- any pattern recognition task which has a fully defined input set with
- appropriate responses can most easily be solved with a look-up table.
-
- I had thought that the principal strength of neural networks (including the
- brain) was the ability to form adaptive responses/rules based on a subset of
- all possible system inputs. If responses are wrong, a neural network has the
- ability to correct itself, whilst improving its response rate on subsequent
- new inputs.
-
- With respect to safety in critical applications, how do you prove a system to
- be correct? You first have to determine every possible input to that system.
- A great deal of time and money has gone into developing tools for proving the
- correctness of software. The general opinion of the researchers in this field
- is that for practical real time applications, it is not feasible to prove
- software correct, no matter how critical the application. The same problem
- applies to computer hardware. Many companies will only use a particular
- component years after it has been introduced, assuming that any faults will
- have surfaced and been corrected in that time. The probability of an error is
- small, but exists.
-
- It is never possible to eliminate errors from any real system no matter how
- good it looks on paper. The current approach to this problem is redundancy.
- Build a number of systems from different component running different software
- and make sure they all produce the same response during use. Is this not one
- of the strengths of NNs? If a cell fails or a connection is broken, the
- degradation of the response to each input is slight.
-
- Neural networks, like fuzzy logic have the advantage of being able to produce
- sensible responses to new inputs. In handwritten OCR for example, reading a
- character at a time be it by a human, ANN, or some other technique, must give a
- recognition rate of less than 100%. Everyone writes differently and no system
- could be trained on examples of every human beings writing. The error rate can
- be reduced if context is included, but not removed. If the NN is correctly
- designed, ambiguous characters can at least be highlighted and alternatives
- suggested with appropriate weightings.
-
- When an ANN misclassified an input, how close is the generated response to the
- correct response. From my experience the differences are small. Personally I
- feel a lot happier with a pilot (with their NN which makes mistakes) flying an
- air-craft rather than a computer. When the unforeseen event occurs, the pilot
- can make a choice based on experience which has a chance of being correct. If
- the computer is exposed to an unforeseen event, the air-craft will almost
- certainly crash.
-
- ----
- Robert B Lambert
- University of Strathclyde
- Scotland, UK.
-
- robert@cs.strath.ac.uk
-