46.txt

This complete matlab for neural network

Most scientists keep a research notebook. You should too. You've probably been
 told this in every science class since fifth grade, but it's true. Different 
systems work for different people; experiment. You might keep it online or in 
a spiral notebook or on legal pads. You might want one for the lab and one for
 home.

Record in your notebook ideas as they come up. Nobody except you is going to r
ead it, so you can be random. Put in speculations, current problems in your wo
rk, possible solutions. Work through possible solutions there. Summarize for f
uture reference interesting things you read.

Read back over your notebook periodically. Some people make a monthly summary 
for easy reference.

What you put in your notebook can often serve as the backbone of a paper. This
 makes life a lot easier. Conversely, you may find that writing skeletal paper
s---title, abstract, section headings, fragments of text---is a useful way of 
documenting what you are up to, even when you have no intention of ever making
 it into a real paper. (And you may change your mind later.)

You may find useful Vera Johnson-Steiner's book Notebooks of the Mind, which, 
though mostly not literally about notebooks, describes the ways in which creat
ive thought emerges from the accumulation of fragments of ideas.

6. Writing
There's a lot of reasons to write.

·   You are required to write one or two theses during your graduate student 
career: a PhD and maybe an MS, depending on your department. 

·   Writing a lot more than that gives you practice. 

·   Academia runs on publish-or-perish. In most fields and schools, this star
ts in earnest when you become a professor, but most graduate students in our l
ab publish before they graduate. Publishing and distributing papers is good po
litics and good publicity. 

·   Writing down your ideas is the best way to debug them. Usually you will f
ind that what seemed perfectly clear in your head is in fact an incoherent mes
s on paper. 

·   If your work is to benefit anyone other than yourself, you must communica
te it. This is a basic responsibility of research . If you write well more peo
ple will read your work! 

·   AI is too hard to do by yourself. You need constant feedback from other p
eople. Comments on your papers are one of the most important forms of that. 


Anything worth doing is worth doing well.

·   Read books about how to write. Strunk and White's Elements of Style gives
 the basic dos and don'ts. Claire Cook's The MLA's Line By Line (Houghton Miff
lin) is about editing at the sentence level. Jacques Barzun's Simple and Direc
t: A Rhetoric for Writers (Harper and Row, 1985) is about composition. 

·   When writing a paper, read books that are well-written, thinking in backg
round mode about the syntactic mechanics. You'll find yourself absorbing the a
uthor's style. 

·   Learning to write well requires doing a lot of it, over a period of years
, and getting and taking seriously criticism of what you've written. There's n
o way to get dramatically better at it quickly. 

·   Writing is sometimes painful, and it can seem a distraction from doing th
e ``real'' work. But as you get better at it, it goes faster, and if you appro
ach it as a craft, you can get a lot of enjoyment out of the process for its o
wn sake. 

·   You will certainly suffer from writer's block at some point. Writer's blo
ck has many sources and no sure cure. Perfectionism can lead to writer's block
: whatever you start to write seems not good enough. Realize that writing is a
 debugging process. Write something sloppy first and go back and fix it up. St
arting sloppy gets the ideas out and gets you into the flow. If you ``can't'' 
write text, write an outline. Make it more and more detailed until it's easy t
o write the subsubsubsections. If you find it really hard to be sloppy, try tu
rning the contrast knob on your terminal all the way down so you can't see wha
t you are writing. Type whatever comes into your head, even if it seems like g
arbage. After you've got a lot of text out, turn the knob back up and edit wha
t you've written into something sensible. 

Another mistake is to imagine that the whole thing can be written out in order
. Usually you should start with the meat of the paper and write the introducti
on last, after you know what the paper really says. Another cause of writer's 
block is unrealistic expectations about how easy writing is. Writing is hard w
ork and takes a long time; don't get frustrated and give up if you find you wr
ite only a page a day.

·       Perfectionism can also lead to endless repolishing of a perfectly ade
quate paper. This is a waste of time. (It can also be a way of semideliberatel
y avoiding doing research .) Think of the paper you are writing as one stateme
nt in a conversation you are having with other people in the field. In a conve
rsation not everything goes perfectly; few expect that what they say in a sing
le utterance will be the whole story or last word in the interchange. 

·       Writing letters is good practice. Most technical papers would be impr
oved if the style was more like a letter to a friend. Keeping a diary is also 
a way to practice writing (and lets you be more stylistically experimental tha
n technical papers). Both practices have other substantial benefits. 

·       It's a common trap to spend more time hacking the formatter macrology
 than the content. Avoid this. LaTeX is imperfect, but it has most of the macr
ology you want. If that's not enough, you can probably borrow code from someon
e else who has wanted to do the same thing. Most sites (including MIT ) mainta
in a library of locally-written extensions. 

·       Know what you want to say. This is the hardest and most important fac
tor in writing clearly. If you write something clumsy and can't seem to fix it
, probably you aren't sure what you really want to say. Once you know what to 
say, just say it. 

·       Make it easy for the reader to find out what you've done. Put the sex
y stuff up front, at all levels of organization from paragraph up to the whole
 paper. Carefully craft the abstract. Be sure it tells what your good idea is.
 Be sure you yourself know what it is! Then figure out how to say it in a few 
sentences. Too many abstracts tell what the paper is generally about and promi
se an idea without saying what it is. 

·       Don't ``sell'' what you've done with big words or claims. Your reader
s are good people; honesty and self-respect suffice. Contrariwise, don't apolo
gize for or cut down your own work. 

·       Often you'll write a clause or sentence or paragraph that you know is
 bad, but you won't be able to find a way to fix it. This happens because you'
ve worked yourself into a corner and no local choice can get you out. You have
 to back out and rewrite the whole passage. This happens less with practice. 


·       Make sure your paper has an idea in it. If your program solves proble
m X in 10 ms, tell the reader why it's so fast. Don't just explain how your sy
stem is built and what it does, also explain why it works and why it's interes
ting. 

·       Write for people, not machines. It's not enough that your argument be
 correct, it has to be easy to follow. Don't rely on the reader to make any bu
t the most obvious deductions. That you explained how the frobnitz worked in a
 footnote on page seven is not a justification when the reader gets confused b
y your introducing it without further explanation on page twenty-three. Formal
 papers are particularly hard to write clearly. Do not imitate math texts; the
ir standard of elegance is to say as little as possible, and so to make the re
ader's job as hard as possible. This is not appropriate for AI. 

·       After you have written a paper, delete the first paragraph or the fir
st few sentences. You'll probably find that they were content-free generalitie
s, and that a much better introductory sentence can be found at the end of the
 first paragraph of the beginning of the second. 

If you put off writing until you've done all the work, you'll lose most of the
 benefit. Once you start working on a research project, it's a good idea to ge
t into the habit of writing an informal paper explaining what you are up to an
d what you've learned every few months. Start with the contents of your resear
ch notebook. Take two days to write it---if it takes longer, you are being per
fectionistic. This isn't something you are judged on; it's to share with your 
friends. Write DRAFT---NOT FOR CITATION on the cover. Make a dozen copies and 
give them to people who are likely to be interested (including your advisor!).
 This practice has most of the benefits of writing a formal paper (comments, c
larity of thought, writing practice, and so forth), but on a smaller scale, an
d with much less work invested. Often, if your work goes well, these informal 
papers can be used later as the backbone of a more formal paper, from an AI La
b Working Paper to a journal article.

Once you become part of the Secret Paper Passing Network, you'll find that peo
ple give you copies of draft papers that they want comments on. Getting commen
ts on your papers is extremely valuable. You get people to take the time to wr
ite comments on yours by writing comments on theirs. So the more people's pape
rs you write comments on, the more favors are owed you when you get around to 
writing one... good politics. Moreover, learning to critique other people's pa
pers will help your own writing.

Writing useful comments on a paper is an art.

·       To write really useful comments, you need to read the paper twice, on
ce to get the ideas, and the second time to mark up the presentation. 

·       If someone is making the same mistake over and over, don't just mark 
it over and over. Try to figure out what the pattern is, why the person is doi
ng it, and what they can do about it. Then explain this explicitly at length o
n the front page and/or in person. 

·       The author, when incorporating your comments, will follow the line of
 least resistance, fixing only one word if possible, or if not then one phrase
, or if not then one sentence. If some clumsiness in their text means that the
y have to back up to the paragraph level, or that they have to rethink the cen
tral theme of a whole section, or that the overall organization of the paper i
s wrong, say this in big letters so they can't ignore it. 

·       Don't write destructive criticism like ``garbage'' on a paper. This c
ontributes nothing to the author. Take the time to provide constructive sugges
tions. It's useful to think about how you would react to criticism of your own
 paper when providing it for others. 

There are a variety of sorts of comments. There are comments on presentation a
nd comments on content. Comments on presentation vary in scope. Copy-edits cor
rect typos, punctuation, misspellings, missing words, and so forth. Learn the 
standard copy-editing symbols. You can also correct grammar, diction, verbosit
y, and muddied or unclear passages. Usually people who make grammatical mistak
es do so consistently, using comma splices for example; take the time to expla
in the problem explicitly. Next there are organizational comments: ideas out o
f order at various scales from clauses through sentences and paragraphs to sec
tions and chapters; redundancy; irrelevant content; missing arguments.

Comments on content are harder to characterize. You may suggest extensions to 
the author's ideas, things to think about, errors, potential problems, express
ions of admiration. ``You ought to read X because Y'' is always a useful comme
nt.

In requesting comments on a paper, you may wish to specify which sorts are mos
t useful. For an early draft, you want mostly comments on content and organiza
tion; for a final draft, you want mostly comments on details of presentation. 
Be sure as a matter of courtesy to to run the paper through a spelling correct
or before asking for comments.

You don't have to take all the suggestions you get, but you should take them s
eriously. Cutting out parts of a paper is particularly painful, but usually im
proves it. Often if you find yourself resisting a suggestion it is because whi
le it points out a genuine problem with your paper the solution suggested is u
nattractive. Look for a third alternative.

Getting your papers published counts. This can be easier than it seems. Basica
lly what reviewers for AI publications look for is a paper that (a) has someth
ing new to say and (b) is not broken in some way. If you look through an IJCAI
 proceedings, for example, you'll see that standards are surprisingly low. Thi
s is exacerbated by the inherent randomness of the reviewing process. So one h
euristic for getting published is to keep trying. Here are some more:

·       Make sure it is readable. Papers are rejected because they are incomp