PDA

View Full Version : Woohoo!! I rule!



The V.
10-17-2001, 08:53 PM
*looks around to see if anyone's watching*

*makes his first post in Gen. Forum*

Well, I spent ~18 hours the past 3 days creating classes to do a multilayer perceptron (one type of neural network) for my ANN class. And it's FINALLY done.

And, as a bonus, it works really well! :D My secret combination of science and sorcery actually does a great job.

doubleanti
10-17-2001, 11:55 PM
>science and sorcery

right on!

greenRoom
10-18-2001, 12:04 AM
"~18 hours the past 3 days" == ~6 hours/day

weak...

but congratulations none the less!

oskilian
10-18-2001, 11:09 AM
my congratulations depend on what does your program do?

Oskilian

-KEN-
10-18-2001, 11:45 AM
Your first post in the GD forum??

Let's have a party!

rick barclay
10-18-2001, 01:20 PM
With a user name like that, you gotta be female.

rick barclay

Pendragon
10-18-2001, 01:21 PM
...You rule?

I ROCK!!:D

-Penny

gamegod3001
10-18-2001, 03:04 PM
So
-Ken- and myself I are perfect.

doubleanti
10-18-2001, 11:01 PM
>With a user name like that, you gotta be female.

why's that rick?

greenRoom
10-18-2001, 11:08 PM
think about it...

doubleanti
10-18-2001, 11:13 PM
::thinks, hurts self::

does it have to do with sex or something? i'm lost...

Troll_King
10-18-2001, 11:25 PM
I wrote a C++ program a couple days ago, although not too complex it involved inheritance, virtual methods, separte file compilation, and sorting an array of pointers to class objects. This is not too difficult but I was happy none the less. I don't have a lot of expierience with C++.

Congratulations on your own program.

EvenFlow
10-18-2001, 11:48 PM
>>::thinks, hurts self::
does it have to do with sex or something? i'm lost...<<

When a man loves a woman, or a woman loves a woman, or a man loves a man, or a man loves a man and a woman, or a woman loves a woman and a man, or when a man loves a goat...

doubleanti
10-19-2001, 12:01 AM
>When a man loves a woman, or a woman loves a woman, or a man loves a man, or a man loves a man and a woman, or a woman loves a woman and a man, or when a man loves a goat...

still lost...

EvenFlow
10-19-2001, 12:12 AM
Okay I was trying to get some laughs there, but anyway :rolleyes:

Think of the female anatomy doubleanti (I know it must be hard to being a 17 yo male lol).

doubleanti
10-19-2001, 12:20 AM
oh... well chyrist sakes... i would have thought you all wouldn't be thinking of that 24-7, but you guys do fit that sterotype of the male humanity... that truly sickens me...

EvenFlow
10-19-2001, 12:26 AM
>>but you guys do fit that sterotype of the male humanity... that truly sickens me...

Sickens you? You must be female then.

-KEN-
10-19-2001, 08:25 AM
Damnit, Ray! Reveal your gender to us in a spectacular spread labeled "My Gender! At Long Last!" Now go on - get posting!

The V.
10-19-2001, 01:34 PM
I'm a guy, if anyone cares, and I hadn't even THOUGHT of my nichname in that light.

I like having a one character name (too bad I couldn't register as just "V") -- it makes me more of an international man of mystery=]

BTW, the final printout of my code was some 30+ pages, pretty densely packed, too. Turned it in today, man, am I glad that's over. Total that homework cost me over 36 hours, and I only had a few days when I could do it. And yes, I did spend, last night, 16 hours working nonstop (except for the travel time when I needed to go to a lab to test something). Worked on it from 4 PM to 8 AM.

Garfield
10-19-2001, 01:38 PM
The description of the program sounds tough. Was it hard coding?

greenRoom
10-19-2001, 02:42 PM
"16 hours working nonstop "

now that's what i'm talkin about!, excuse my last reply.

The V.
10-19-2001, 04:17 PM
Originally posted by Garfield
The description of the program sounds tough. Was it hard coding?

Not really. Some of the stuff took some time -- I created a Matrix class to handle all kinds of linear algebra, which was time consuming. I chose this over pre-existing libraries specifically because a) I've had ........ poor luck getting performance out of existing classes, and b) I've never found Matrix classes that support all of the necessary operations I wanted.

A lot of the time was in simply running the datasets, and fine tuning. I ran many of the datasets 30 or so times, with various parameter changes, to determine the best values for maybe 4 or 5 parameters. Just changing these parameters DRASTICALLY changes the convergence of the network -- I could often double or even triple classification rates simply by playing with parameters to make it more likely to converge to a global minima.

Plus, some of the questions wanted some strange things. For example, one problem wanted me to run the algorithm until I noticed a particular feature of the hidden node outputs (basically, these are temporary values, computed from the inputs, used to computer the final outputs). It took me 60 runs to see this feature, and so even though my network had 100% classification rate, I had to continue to run it until I saw this special feature.

EvenFlow
10-19-2001, 06:45 PM
>>Damnit, Ray! Reveal your gender to us in a spectacular spread labeled "My Gender! At Long Last!" Now go on - get posting!

Well there was no reply by doubleanti was there? So my last guess could've been right.

Aran
10-19-2001, 06:49 PM
hee... our good friend mr. ray, here, has had you all stumped for plenty of time.

i, on the other hand, have known all along!

bwahahahah!

Garfield
10-19-2001, 09:19 PM
Okay, The V., can you actaully explain what the program is supposed to do:

> classes to do a multilayer perceptron (one type of neural network) for my ANN class.

Explain this. I don't really understand. Sounds interesting, though.

--Garfield

The V.
10-20-2001, 01:26 AM
Well, a neural network is a "learning machine". Basically, you write a program that, when given training data, "learns" various features of the data, and uses this to make generalizations or predictions.

An example is the original data I tested this MLP with -- it is a set of measurements taken from iris flowers, with each sample taken from an iris of one of three types. The goal is to have the network learn how to distinguish among iris flowers based solely on this data.

So, the real test of the network is given testing data, can it correctly classify an iris into the proper class? And the answer, in my case, is yes, it can do it with above 90% correctness (97.3% was the best I've achieved).

The idea behind neural networks are that computers, working mathematically, can analyze data and find patterns within that are far too complicated for people to derive themselves. For example, for the iris data, there IS a mathematical equation you could write which would give you the ability to classify 97.3% of all iris flowers correctly. But this function is very complicated, and to try to figure out what the function is on pencil and paper would take ages for a person to accomplish. Because computers can do math vastly faster than humans, the goal of a neural network program is to create a mathematical model which the computer will follow that will eventually yield the function you want -- in this example, you want the function to tell you what kind of iris you have.

So, what you do is create a neural network program. The network takes however many inputs you want to feed it, and generates the desired number of outputs. You give it training data, you give it rules as to how it is supposed to learn, and you see how well it does.

EvenFlow
10-20-2001, 02:55 AM
I've got a class for my degree next year called Decision Support Systems. Apparently we get to do some basic (!) neural network programming. You wouldn't happen to know of some good sites or books I could read about NN?

Garfield
10-20-2001, 07:47 AM
The V., that sounds awesome! Very interesting program. By that description, it sounds like one of those programs that is fun to program. Not dreading it when you have to program it. That is definitely neat, though.

--Garfield

oskilian
10-20-2001, 09:25 AM
what compiler did you use?

Oskilian

The V.
10-20-2001, 11:35 AM
I used Borland C++ 5.02, which is what I do a lot of programs in, being as it was free, it has an IDE, and is mostly OK in most respects. It's NOT fully ANSI C++ compliant, though, which always bugs me when it causes problems...

Neural network programming IS fun stuff. It's the ONLY class that I've had where the homework problems are actually useful beyond the scope of the course.

The only book on neural networks that I've used so far is the book for the class, and unfortunately I haven't read it as much as I should -- I prefer the lectures, which give all the information needed and are explained better. The book does explain things, but sometimes you really have to pick apart the sentences to understand what they're saying, because they love to densely pack information into sentences.

The book, in case others wondered, is Neural Networks: A Comprehensive Foundation, by Simon Haykin. It's decent, although you better remember your calculus. I suppose that's true for any NN bok, though, unless they completely leave out the explanations of how they work. There's always a lot of math.

Luckily, often it simplifies incredibly, so implementation isn't as hard as you might think.

Garfield
10-20-2001, 04:30 PM
> There's always a lot of math.
I figured this subject would come in use sometime.

--Garfield

Xterria
10-20-2001, 05:33 PM
:eek:MOOOOOOOOOOOOOOOOOOOO!!!!:eek:

Garfield
10-20-2001, 07:13 PM
What???

greenRoom
10-21-2001, 12:34 AM
Garfield, i noticed you mention surfing (in the ocean) as one of your interests. cool man, me too! as you can see from my avatar (well kind of a small pic, can't see too well; just changed it earlier today because i wanted it to reflect my name more). but actually.. i have'nt surfed for like maybe over a year; man i used to always surf in my teen years though (like every day practically; from like 13 - 18 yrs. old). i need to get back out there soon!

Garfield
10-21-2001, 05:04 AM
> i need to get back out there soon!
You need to get back out there now! Surfing is life.

Aran
10-21-2001, 10:37 AM
no, programming is life. DUH!

Garfield
10-21-2001, 11:01 AM
> no, programming is life. DUH!

Agreement:
Programming while you surf is life!

--Garfield

Aran
10-21-2001, 11:05 AM
good enough for me :D

Garfield
10-21-2001, 11:06 AM
My two favorite things (besides my religion):

Surfing & Programming

Aran
10-21-2001, 11:25 AM
i love my lack of religion... I'm infinitely thankful for not believeing in God, it makes life so much easier to live and so much more fun at the same time. Ethics are pliable and fun as opposed to morals which are rigid and become useless over time. But lets not discuss that.

Music and Programming is my life.

Garfield
10-21-2001, 12:09 PM
> Music and Programming is my life.
Music is definitely great. But surfing is...is...amazing.

Aran
10-21-2001, 01:35 PM
i don't surf because...i...don't... belive...in water?
sounds good enough for me.

Garfield
10-21-2001, 02:16 PM
> sounds good enough for me.
Sure, fine.