|
20 hours staring at this damn Wikipedia article[^] and re-reading the poorly written chapter 5 in Jeff Heaton's book[^]!
I decided early on to skip Jeff's code (which is rather poor) and rewrite each example myself!
I had to say the backpropagation training method was a bit of a challenge for me ...
But 20 hours later I got the same result that Jeff with a program which is not only (objectively) much shorter, (subjectively) much more readable and (objectively) 6 times faster! Yoohoo!   
|
|
|
|
|
I clicked on the Wiki link, and...TLDR!
Bad command or file name. Bad, bad command! Sit! Stay! Staaaay...
|
|
|
|
|
|
It's a software version of a feedback loop.
Yes I know it's not correct per se, it's a simile dammit. 
|
|
|
|
|
Oooh! Nueural Networks...I did my major project at Uni with an MLP, I am trying to find the book I used for to find out about back propergation. It wasn't that one I seem to remember It was an Addison Wesley book, sub £10 paper back, beaten to hell, had examples in HP basic (which I had to port over to C with mixed results), the joy of my little robot learning to go left rather straight ahead (and then the training set blowing the stack point out of the 80C164)!!!
|
|
|
|
|
Ho... additional challenges! 
|
|
|
|
|
Wow ! Consanginousratulations ... and sheepest simpaticosahedrons ... hope you get some good sleep, soon
Can we look forward to an article ?
cheers, Bill ... also brain-stir-fried currently, but not from chasing Goddess Techne's skirts.
«I want to stay as close to the edge as I can without going over. Out on the edge you see all kinds of things you can't see from the center» Kurt Vonnegut.
|
|
|
|
|
Mm.... was wondering about it...
Might finish the book first, and the other book...
And publish that with my A* article in an all rounder AI article! ^^
Speaking of which.. I also found this other interesting link / free eBook!
http://neuralnetworksanddeeplearning.com/index.html[^]
|
|
|
|
|
I prefer "short" solution, because it normally means that "complexity" have to be killed. 
Press F1 for help or google it.
Greetings from Germany
|
|
|
|
|
me too!
but just in case people argue I didn't make use of enough function call! 
|
|
|
|
|
...you spend 15 minutes trying everything to get the debugger to break on a statement only to realise that you've built in Release mode.
cheers
Chris Maunder
|
|
|
|
|
Yeah is this fun or what.
|
|
|
|
|
OK, here you go:
break;
What do you get when you cross a joke with a rhetorical question?
The metaphorical solid rear-end expulsions have impacted the metaphorical motorized bladed rotating air movement mechanism.
Do questions with multiple question marks annoy you???
|
|
|
|
|
You've already got a kit-kat?
"When I was 5 years old, my mother always told me that happiness was the key to life. When I went to school, they asked me what I wanted to be when I grew up. I wrote down 'happy'. They told me I didn't understand the assignment, and I told them they didn't understand life." - John Lennon
|
|
|
|
|
When you say "try everything", what dI'd you try?
Try Grapple for Android, it has a naked pixel guy in it!
Also, loads of blood and some snakes.
|
|
|
|
|
 At least you realized this after 15 minutes and not like, 2 hours.
|
|
|
|
|
It happens, regardless how clever you are, how informed you are.
|
|
|
|
|
Yeah, it's lack of breaks, nothing to do with getting old
|
|
|
|
|
Debugging release versions is no problem, provided you decide up front that you want that ability and build it in. Eh.
|
|
|
|
|
I once spent an entire morning on that... 
On the plus side I did get my break as it was lunch time when I figured it out
|
|
|
|
|
My understanding is that obviously the divide & conquer sorting algorithms of O( n log n ) are far better than the ones of O( n^2 ), except for the case of a small size of data, in which insertion sort is used, as even it is is better than bubble sort.
But it was my experience learning BASIC and then later FORTRAN that bubble sort was introduced as a "read & type in" algorithm. (It was only later when I studied C that I learned about these far better sort algorithms.) So I wonder why is bubble sort even taught? The only explanation I can come up with is that is only a few lines long, with a double for loop (i.e., a very elementary CS concept), so it is easy to "plug & chug" into a program that requires it, without going into the theory of sorting algorithms - and as well would have been useful in the days of the small-byte program, when every line of code was valuable.
Is there some use of this that I am missing here? I suppose that back in the quaint days of "book distribution" (i.e., the only inexpensive way to transfer program code was to put it in a book and have the user type it in, LOL), using bubble sort saved on tedious typing as well.
|
|
|
|
|
|
No!!! For data size less than 16, a bubble sort is faster. Much less setup overhead. Do the math!
Gus Gustafson
|
|
|
|
|
|
gggustafson wrote: For data size less than 16, a bubble sort is faster. Much less setup overhead. Do the math
This is an assertion for which evidence is thin. For what O(n log n) sorts is this true? My experience with algorithms I have been measuring lately is that for very small n, the performance of sorts is indistinguishable, but not that O(n2) sorts were faster.
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
