NNEA start to develop a new version of neural network pattern recognizer. After investigating the results of our previous version pattern recognizer we decide to fix center of data window to get a better currency forecasts results.

Now the last price is the center of the forecast window. We expect better forecasting quality. Also we plan use different neural networks for different periods and currencies. And in this version we use sigmoid function in neurons.

This is called the log-sigmoid because a sigmoid can also be constructed using the hyperbolic tangent function instead of this relation, in which case it would be called a tan-sigmoid. Here, we will refer to the log-sigmoid as simply “sigmoid”. The sigmoid has the property of being similar to the step function, but with the addition of a region of uncertainty. Sigmoid functions in this respect are very similar to the input-output relationships of biological neurons, although not exactly the same. Below is the graph of a sigmoid function. Sigmoid functions are also prized because their derivatives are easy to calculate, which is helpful for calculating the weight updates in certain training algorithms.

And here is the first results. It's much better than previous. Here are first results.

This is realy good results.

Now the developing was finished. You can learn more about this indicator by following this link Neural Network Trend Predictor