Scribd
Upload
11 views1 page

Neural Network Input and Output Explained

The document outlines the components of a neural network, including inputs such as customer duration and tips, biases to adjust function amplitude, and outputs for comparison with target values. It describes weights that amplify inputs, the summation of inputs with weights, and the function used to scale inputs for generating outputs. Additionally, it references hidden neurons and the predicted values for comparison with expected outputs.

Uploaded by

caioc.restivo
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
11 views1 page

Neural Network Input and Output Explained

The document outlines the components of a neural network, including inputs such as customer duration and tips, biases to adjust function amplitude, and outputs for comparison with target values. It describes weights that amplify inputs, the summation of inputs with weights, and the function used to scale inputs for generating outputs. Additionally, it references hidden neurons and the predicted values for comparison with expected outputs.

Uploaded by

caioc.restivo
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd

Q1: The inputs, in case the duration the customer stayed and the tip.

Q2: The bias, an internal value to increase the amplitude of the function.

Q3: The output to be compared to the target values 𝑦.

𝑤21(1): the weight that will amplify the input (the second input going to the
upper neuron of the hidden layer). It is called weight.

Σ: the sum of the inputs with their weights.

f: the function that the input will be scaled with in order to generate the output.

Box A: hidden components, the neurons.

Box B: output.

^y: predicted values to be compared with the expected output.

You might also like