• Forum
  • Lounge
  • Need me some pedagogical style help with

 
Need me some pedagogical style help with neural networking! Its that backprogation maths init, know anything about it?

So I been learning me computerscience at uni, am actually about to start the second year, I did a foundation and the first year so technically I re learned a foundation twice again so my foundation must be sooo solid by now.

My maths will be good enough too, by the third year that is thats when I can choose neural networking as a module however its pretty hard very soon and I doubt I will do well lest I start know.

Thats why I took out a load of "foundation to neural networking" books, these books are very much for people who already know what the words mean it seems, I researched my issues with this type of book, I need pedagogical lernings and shit.

Just I still could use someone hold my hand though, and nother thing, get to re learn all my c++, it wasnt so good last time I was here but I think I am really profesesional now, my code is all readable and modular, just think i need some actual computer science help.

who's in?

If I get no help I might record my experiences as an article, but maybe not about neural networking but about approaching a subject and learning it pedamogogicaly.
I might be able to help with back propagation if you have a specific question or issue.
Well thanks I don't really know where to start to learn, I can program your basic little guessing neuron but I dont get much further study wise, how did you learn the subject?
I took an ML course where there was a neural network component. I learned some things about the subject, such as how feed forward neural networks work mathematically, and how to apply them. My advice is to find some neural networking course materials online somewhere. Look for some assignments and try to complete them.
Last edited on
first thing that comes up with ML course is mountain leader, im looking for some relavant homework, simple advice is good advice, I will show you what I find though just incase I dont know if its not actualy helpful.
Recommended Background

Programming proficiency in Matlab, Octave or Python. Enough knowledge of calculus to be able to differentiate simple functions. Enough knowledge of linear algebra to understand simple equations involving vectors and matrices. Enough knowledge of probability theory to understand what a probability density is.


https://www.coursera.org/course/neuralnets

From my experience, these prerequisites were very important to doing well.
Last edited on
Yeah I found that :D thanks! these pre-requisites have stumped me before, perfect really; linearregression you are a bastard and I will destroy you.
Topic archived. No new replies allowed.