How to Use Neural Code Neural Predictor

How to Use Neural Code Neural Predictor thumbnail
Neurons are brain cells.

Neurons are brain cells. Artificial neural networks are engineering simulations -- in hardware or software -- that behave like interconnected neurons. Neural coding is the pattern of stored information in biological or artificial neural networks that allow them to give an appropriate response for a specific pattern of excitations. The neural code is developed by repeatedly exposing the neural net to excitation patterns and comparing their outputs to known correct outputs -- adjusting the neural code each time so that the response is a little more appropriate. If the training examples consist of time-related stimulus-response information, the neural net can learn to be predictive.

Things You'll Need

  • Training data
  • Neural network
Show More

Instructions

    • 1

      Train the neural network to set its neural code. After the neural code is set properly, the neural net will act as a predictor. When shown a pattern of inputs, it will predict the appropriate output.

    • 2

      Divide the training data into two random sets. Call the sets the "training" set and the "testing" set. Present each example from the training set to the neural net and check its response against the proper response. Use one of the updating algorithms to adjust the neural code to move the actual answer closer to the correct answer. Cycle through the examples in the training set several times.

    • 3

      Test the predictive accuracy of the neural coding by presenting the examples in the testing set to the neural net. Do not change the neural code during the testing phase. This phase determines how well this specific neural coding is working.

    • 4

      Verify that the trained neural net has the neural coding to accurately predict the phenomena that you trained it to predict. If it does not, you need to retrain it with new data -- perhaps a bigger or more diverse training set. If the net still does not behave correctly, you need new network architecture or a different training algorithm.

Tips & Warnings

  • An example of a case in which neural nets have been trained to predict accurately is in temperature forecasting. Every weather station takes temperature readings every day, so training data is easy to come by. After training such a net, you can input the temperature in the surrounding locations and get a prediction of your temperature in 24 hours.

  • It is tempting to think that if you train a neural net more, it will work better; this is not always true. Training should stop after the net accurately predicts everything in the training set. Training that continues more than one or two cycles through the training set after reasonable accuracy is achieved can produce “overtraining,” where the neural net’s ability to generalize decreases and its ability to predict anything other than the training set declines.

Related Searches

References

Resources

  • Photo Credit Comstock Images/Comstock/Getty Images

Related Ads

Featured
View Mobile Site