NeuroLab
Build 7
NeuroLab is a tool that lets you build Neural Network indicators in Wealth-Lab using drag and drop.
$49.95 / Lifetime OR included in Premium subscription
* all Extensions require a Wealth-Lab 7 Subscription

NeuroLab is a tool that lets you build Neural Network indicators in Wealth-Lab using drag and drop. You can drag any number of indicators into the Neural Network's Input Layer, establish the architecture of the Hidden Layer(s), and specify the indicator to predict in the Output Layer (typically ROC, which is percentage change, or LogReturn).

You then select a DataSet, and train the Neural Network. When the training is completed, you have a new instance of the Neural Network indicator (NNPredictor) that you can use in any chart, Building Block, or C# Coded Strategy.

Screenshots

Define Inputs Without a Script!
Use the Add Neuron button or drag and drop any number of indicator to create your neural network input layer. Each Neuron is represented by a configurable rectangular user interface block.
Configure Hidden Layers and Hyperparameters
Add layers and set the number of Neurons and Activation Function for each one. How hard is it to add hidden layers? Let's find out!
Train the Neuro Network Predictor
After setting the in-sample and out-of-sample data ranges, put all your CPU cores to work on training your NNP. While waiting, reward youself with a cafe!
Evaluate the NNP on In and Out-of-Sample Data
You've finished training (and optimizing) your neural network on in-sample data. Now get a visual confirmation if the network as good at predicting using data that the NNP hasn't seen yet, i.e., the out-of-sample data.
Drag and Drop Your NNP Indicator
Save your work, drop your NNP indicator into a chart or building block strategy, and if you've found the proverbial crystal ball, don't tell anyone else except the Wealth-Lab team!

Change Log

Build 7 - 10/21/2021
  • Build required to interface with some new charting changes in WL7 Build 28.
Build 6 - 9/29/2021
  • Flag the NNP indicator as a lengthy calculation, so it doesn't get enabled by default in Indicator Profiler.
  • Sort order is now retained when list results are copied to clipboard.
Build 5 - 9/6/2021
  • Integrate NeuroLab's chart with the WL7 Linked Charting.
Build 4 - 8/7/2021
  • Added multi-column sort support.
Build 3 - 6/22/2021
  • You can now set the recommended learning rate in the HyperParameters page based on the selected Optimization Method.
Build 2 - 6/3/2021
  • Established more realistic default values.
Build 1 - 5/20/2021

Baseline release.

Discussions