nn.faq

本例是一个神经网络仿真应用程序

From [e-mail] (Lutz Prechelt)
Newsgroups: comp.ai.neural-nets,comp.answers,news.answers
Subject: FAQ in comp.ai.neural-nets -- monthly posting
Date: 1 Jun 1993 07:35:06 GMT

Archive-name: neural-net-faq
Last-modified: 93/05/20

(FAQ means "Frequently Asked Questions")

  ------------------------------------------------------------------------
        Anybody who is willing to contribute any question or
        information, please email me; if it is relevant,
        I will incorporate it. But: Please format your contribution
        appropriately so that I can just drop it in.

        The monthly posting departs at the 28th of every month.
  ------------------------------------------------------------------------

This is a monthly posting to the Usenet newsgroup comp.ai.neural-nets
(and news.answers, where it should be findable at ANY time)
Its purpose is to provide basic information for individuals who are
new to the field of neural networks or are just beginning to read this 
group. It shall help to avoid lengthy discussion of questions that usually 
arise for beginners of one or the other kind.

>>>>> SO, PLEASE, SEARCH THIS POSTING FIRST IF YOU HAVE A QUESTION <<<<<
                           and
>>>>> DON'T POST ANSWERS TO FAQs: POINT THE ASKER TO THIS POSTING <<<<<

This posting is archived in the periodic posting archive on
host trfm.mit.edu (and on some other hosts as well).
Look in the anonymous ftp directory "/pub/usenet/news.answers",
the filename is as given in the 'Archive-name:' header above.
If you do not have anonymous ftp access, you can access the archives
by mail server as well.  Send an E-mail message to
[e-mail] with "help" and "index" in the body on
separate lines for more information.


The monthly posting is not meant to discuss any topic exhaustively.

Disclaimer: This posting is provided 'as is'.
            No warranty whatsoever is expressed or implied, 
            especially, no warranty that the information contained herein
            is correct or useful in any way, although both is intended.

>> To find the answer of question number <x> (if present at all), search
>> for the string "-A<x>.)" (so the answer to question 12 is at "-A12.)")

And now, in the end, we begin:

============================== Questions ==============================

(the short forms and non-continous numbering is intended)
1.)  What is this newsgroup for ?  How shall it be used ?
2.)  What is a neural network (NN) ?
3.)  What can you do with a Neural Network and what not ?
4.)  Who is concerned with Neural Networks ?

6.)  What does 'backprop' mean ?
7.)  How many learning methods for NNs exist ?  Which ?
8.)  What about Genetic Algorithms ?
9.)  What about Fuzzy Logic ?

10.) Good introductory literature about Neural Networks ?
11.) Any journals and magazines about Neural Networks ?
12.) The most important conferences concerned with Neural Networks ?
13.) Neural Network Associations ?
14.) Other sources of information about NNs ?

============================== Answers ==============================

------------------------------------------------------------------------

-A1.)  What is this newsgroup for ?

The newsgroup comp.ai.neural-nets is inteded as a forum for people who want
to use or explore the capabilities of Neural Networks or Neural-Network-like
structures.

There should be the following types of articles in this newsgroup:

1. Requests

  Requests are articles of the form 
    "I am looking for X"
  where X is something public like a book, an article, a piece of software.

  If multiple different answers can be expected, the person making the 
  request should prepare to make a summary of the answers he/she got
  and announce to do so with a phrase like
    "Please email, I'll summarize"
  at the end of the posting.
  
  The Subject line of the posting should then be something like
    "Request: X"

2. Questions

  As opposed to requests, questions are concerned with something so specific
  that general interest cannot readily be assumed.
  If the poster thinks that the topic is of some general interest,
  he/she should announce a summary (see above).

  The Subject line of the posting should be something like
    "Question: this-and-that"
  or have the form of a question (i.e., end with a question mark)

3. Answers

  These are reactions to questions or requests.
  As a rule of thumb articles of type "answer" should be rare.
  Ideally, in most cases either the answer is too specific to be of general 
  interest (and should thus be e-mailed to the poster) or a summary
  was announced with the question or request (and answers should
  thus be e-mailed to the poster).

  The subject lines of answers are automatically adjusted by the 
  news software.

4. Summaries

  In all cases of requests or questions the answers for which can be assumed
  to be of some general interest, the poster of the request or question 
  shall summarize the ansers he/she received.
  Such a summary should be announced in the original posting of the question
  or request with a phrase like
    "Please answer by email, I'll summarize"

  In such a case answers should NOT be posted to the newsgroup but instead
  be mailed to the poster who collects and reviews them.
  After about 10 to 20 days from the original posting, its poster should 
  make the summary of answers and post it to the net.

  Some care should be invested into a summary:
  a) simple concatenation of all the answers is not enough;
     instead redundancies, irrelevancies, verbosities and
     errors must be filtered out (as good as possible),
  b) the answers shall be separated clearly
  c) the contributors of the individual answers shall be identifiable
     (unless they requested to remain anonymous [yes, that happens])
  d) the summary shall start with the "quintessence" of the answers,
     as seen by the original poster
  e) A summary should, when posted, clearly be indicated to be one
     by giving it a Subject line starting with "Summary:"

  Note that a good summary is pure gold for the rest of the newsgroup
  community, so summary work will be most appreciated by all of us.
  (Good summaries are more valuable than any moderator !  :-> )

5. Announcements

  Some articles never need any public reaction.
  These are called announcements (for instance for a workshop,
  conference or the availability of some technical report or
  software system).

  Announcements should be clearly indicated to be such by giving
  them a subject line of the form
    "Announcement: this-and-that"

6. Reports

  Sometimes people spontaneously want to report something to the
  newsgroup. This might be special experiences with some software,
  results of own experiments or conceptual work, or especially 
  interesting information from somewhere else.

  Reports should be clearly indicated to be such by giving
  them a subject line of the form
    "Report: this-and-that"
  
7. Discussions

  An especially valuable possibility of Usenet is of course that of
  discussing a certain topic with hundreds of potential participants.
  All traffic in the newsgroup that can not be subsumed under one of
  the above categories should belong to a discussion.

  If somebody explicitly wants to start a discussion, he/she can do so
  by giving the posting a subject line of the form
    "Start discussion: this-and-that"
  (People who react on this, please remove the
   "Start discussion: " label from the subject line of your replies)

  It is quite difficult to keep a discussion from drifting into chaos,
  but, unfortunately, as many many other newsgroups show there seems
  to be no secure way to avoid this.
  On the other hand, comp.ai.neural-nets has not had many problems
  with this effect in the past, so let's just go and hope...   :->

------------------------------------------------------------------------

-A2.)  What is a neural network (NN) ?

  [anybody there to write something better?
   buzzwords: artificial vs. natural/biological; units and
   connections; value passing; inputs and outputs; storage in structure
   and weights; only local information; highly parallel operation ]

First of all, when we are talking about a neural network, we *should*
usually better say "artificial neural network" (ANN), because that is
what we mean  most of the time. Biological neural networks are much
more complicated in their elementary structures than the mathematical
models we use for ANNs.

A vague description is as follows:

An ANN is a network of many very simple processors ("units"), each
possibly having a (small amount of) local memory. The units are
connected by unidirectional communication channels ("connections"),
which carry numeric (as opposed to symbolic) data.  The units operate
only on their local data and on the inputs they receive via the
connections.

The design motivation is what distinguishes neural networks from other
mathematical techniques:

A neural network is a processing device, either an algorithm, or actual
hardware, whose design was motivated by the design and functioning of human
brains and components thereof.

Most neural networks have some sort of "training" rule
whereby the weights of connections are adjusted on the basis of
presented patterns.
In other words, neural networks "learn" from examples,
just like children learn to recognize dogs from examples of dogs,
and exhibit some structural capability for generalization.

Neural networks normally have great potential for parallelism, since
the computations of the components are independent of each other.

------------------------------------------------------------------------

-A3.)  What can you do with a Neural Network and what not ?

  [preliminary]
  
In principle, NNs can compute any computable function, i.e. they can
do everything a normal digital computer can do.
Especially can anything that can be represented as a mapping between
vector spaces be approximated to arbitrary precision by feedforward
NNs (which is the most often used type).

In practice, NNs are especially useful for mapping problems
which are tolerant of a high error rate, have lots of example data
available, but to which hard and fast rules can not easily be applied.

NNs are especially bad for problems that are concerned with manipulation 
of symbols and for problems that need short-term memory.

------------------------------------------------------------------------

-A4.)  Who is concerned with Neural Networks ?

Neural Networks are interesting for quite a lot of very dissimilar people:

- Computer scientists want to find out about the properties of 
  non-symbolic information processing with neural nets and about learning 
  systems in general.
- Engineers of many kinds want to exploit the capabilities of 
  neural networks on many areas (e.g. signal processing) to solve 
  their application problems.
- Cognitive scientists view neural networks as a possible apparatus to
  describe models of thinking and conscience (High-level brain function).
- Neuro-physiologists use neural networks to describe and explore
  medium-level brain function (e.g. memory, sensory system, motorics).
- Physicists use neural networks to model phenomena in statistical
  mechanics and for a lot of other tasks.
- Biologists use Neural Networks to interpret nucleotide sequences.
- Philosophers and some other people may also be interested in 
  Neural Networks for various reasons.

------------------------------------------------------------------------

-A6.)  What does 'backprop' mean ?

[anybody to write something similarly short,
 but easier to understand for a beginner ? ]

It is an abbreviation for 'backpropagation of error' which is the
most widely used learning method for neural networks today.
Although it has many disadvantages, which could be summarized in the
sentence