Re: Simple ANN question

Peder Ydalus <[EMAIL PROTECTED]> wrote in message 
news:<[EMAIL PROTECTED]>...
> I'm doing a University project on COM interaction in the win32
> environment using Python, and I figured making an ANN and reading the
> values from an excel sheet would be good project.
> 
> My ANN har 12 imputs. These are all stock data, so there are no bounds
> and the values vary a lot. For instance, a beta value is usually in the
> range <0, 1>, whereas trading volumes are at the extreme more than a
> billion.
> 
> I made a plain ANN with 12 input neurons, 3 hidden neurons and one
> output neuron. The input neurons are a stock ticker id (numbered myself
> from 0 to about 250), a stock industry sector id (numbered myself from 0
> to about 100), the beta value (normally never outside <-1, 2>), date
> (counting days since 01.01.1995), 

Is performance seasonal?

> trading price (highly varying from
> stock to stock), trading volume (varying even more from stock to stock),
> pluss date, price and volume for the day before and the day before that. 
> 
> The output neuron is supposed to propose a price for the next day.

Center and scale all inputs. Use *change* of price as the output.
Choose intial weight values and learning rates wisely. See Tveter's
Home page and the FAQ.

Hope this helps.

Greg
 
> However, as I train, the big input values quickly sets the values in the
> hidden neurons to either 1 or -1. This in turn leads to weight updates
> of 0. My ANN doesn't get passed2 or 3 iterations before I can turn off
> the training.
> 
> Finally, the sigmoid function in the last neuron will, of course, lead
> to an output in the range <0, 1>. Compared to the supposed value, e.g.
> 250, leads to weight updates following an error of about 249.
> 
> What am I not getting?

Scaling & identity output activation
> 
> Yes, I have read the FAQ, but it didn't clear up my misconceptions.
> 
> Finally why do we need biases and bias weights? 

Why do we need the bias b in the linear model

y = m*x + b ?

> And when we do, if they
> are all set to 1 does it really make a difference? 
> 
> Btw, anyone know any good ANN litterature, taking things from the
> basics? I'm using a book called Machine Learning by Mitchell, but want
> something better.
> 
> Thanks!
>  
> - Peder -