2. Probabilities. NI give probabilities of the signals they produce, because if they are providing a sell signal, for example, the closer to 1 the signal is, the stronger the probability of sell. The closer to -1, the stronger the probability of "don't' sell".

3. Unsupervised. NI are "unsupervised" neural networks, meaning that they do not need to be trained by showing them the correct answers, like most neural networks (i.e., "supervised" neural networks). You do not teach them by providing any kind of actual output which they learn to reproduce, as with most neural nets.

4. Evolutionary. NI "learn" how to give their signals based upon evolutionary pressure. The genetic algorithm (GA) in the NeuroShell Trader Professional or NeuroShell DayTrader Professional "evolves" NI that give better and better signals. Survival of the fittest controls the evolutionary process as usual, where fitness is determined by how much money the NI make, or how good they work as inputs to other nets or indicators.

5. Architectures. Although anyone can use NI, neural network aficionados will love them because there are several highly technical neural network "architectures" from which you can choose.

Warning: You do not have to understand how these architectures work in order to build profitable trading systems. You can insert Neural Indicators into your trading systems and let the optimizer find the appropriate settings. Neural Indicators are highly technical from a neural network standpoint, and although they can be used by novices, they can only be fully understood internally by those who have a background in how neural networks function.

a. Ward Nets. This architecture has two different "activation functions" in the hidden neurons. These are called "Ward Nets" since Ward Systems Group invented them many years ago (they first appeared in our classic product NeuroShell 2). The genetic algorithm will find out how to pick the activation functions for you. Ward Nets include Ward2, Ward3, Ward4, Ward5, and Ward6, depending upon the number of inputs.

b. Jump Connections. This architecture has connections directly from inputs to outputs as well as the usual hidden neuron connections. This architecture also features connections from one hidden neuron to the next, like Turboprop 2 has. Jump Nets include Jump2, Jump3, Jump4, Jump5, and Jump6, depending upon the number of inputs.

c. Recurrent Nets. This architecture analyzes not only the current bar of information to produce its signal, but it also reviews a condensed summary of the most recent bars as well. More recent bars receive more weighting than older ones. Recurrent Nets include Recur2, Recur3, Recur4, Recur5, and Recur6.

d. Sparse Nets. These are nets which are not fully connected between the input and hidden neural layers. This means that more inputs can be fed to them without increasing the number of weights drastically. The fact that less information can be stored in sparse weighting connections is compensated for by the fact that less weights allow better optimization. Sparse Nets include Sparse8, Sparse10, and Sparse12.

6. Conditional Versions. We have implemented modified versions of all of the above nets. The conditional version of each of these architectures produces a value of either true or false rather than a value between -1 and 1. Therefore the conditional version of any of the architectures can be used in a Trading Strategy without the necessity of inserting it into an A>B indicator.

7. Generalization. These nets generalize very well, meaning they do not have a strong tendency to "overfit" or "curvefit" like backpropagation neural nets do.

Neural Indicators require the NeuroShell Trader Professional or NeuroShell DayTrader Professional, release 3.2 or better.

For more details, please view the product manual for this add-on