This is machine translation

Translated by Microsoft
Mouseover text to see original. Click the button below to return to the English version of the page.

Note: This page has been translated by MathWorks. Click here to see
To view all translated materials including this page, select Country from the country navigator on the bottom of this page.

Plot Error Histogram

This example shows how to visualize errors between target values and predicted values after training a feedforward neural network.


To run this example, you must be logged in to a MathWorks Account that is licensed to use the Deep Learning Toolbox .

Read Data from the Weather Station ThingSpeak Channel

ThingSpeak™ channel 12397 contains data from the MathWorks® weather station, located in Natick, Massachusetts. The data is collected once every minute. Fields 2, 3, 4, and 6 contain wind speed (mph), relative humidity, temperature (F), and atmospheric pressure (hg) data respectively. Read the data from channel 12397 using the thingSpeakRead function.

data = thingSpeakRead(12397,'Fields',[2 3 4 6],'Numpoints',500...

% Assign input variables
inputs = [data.Humidity'; data.TemperatureF'; data.PressureHg'; data.WindSpeedmph']; 

% Calculate dew point from temperature and relative humidity to use as the target
% Convert temperature from Fahrenheit to Celsius
tempC = (5/9)*(data.TemperatureF-32);
% Specify the constants for water vapor (b) and barometric pressure (c)
b = 17.62;
c = 243.5;
% Calculate the intermediate value 'gamma'
gamma = log(data.Humidity/100) + b*tempC ./ (c+tempC);
% Calculate dew point in Celsius
dewPointC = c*gamma ./ (b-gamma);
% Convert to dew point in Fahrenheit
dewPointF = (dewPointC*1.8) + 32;

% Assign target values for the network
targets = dewPointF'; 

Create Two-Layer Feedforward Network

Use the feedforwardnet function to create a two-layer feedforward network. The network has one hidden layer with 10 neurons and an output layer.

net = feedforwardnet(10);

Train the Feedforward Network

Use the train function to train the feed-forward network.

[net,tr] = train(net,inputs,targets);

Use the Trained Model to Predict Data

After the network is trained and validated, you can use the network object to calculate the network response to any input. For example, you can predict the values of temperature for a vector of humidity values.

outputs = net(inputs);

Plot the Error Histogram

Compute the error values as the difference between target values and predicted values.

error = targets - outputs;
number_of_bins = 10;

This plot shows the error histogram with 10 bins.

See Also