The number of hidden neurons should be 2/3 the size of the input layer, plus the size of the output layer. 2. An autoencoder's job cannot be reduced to creating a representation of the input data that can fit in smaller vectors. Another rule is equal to 2/3 size of input layer and output layer .
The number of hidden neurons should be less than twice the size of the input layer.
At the current time, the network will generate 4 outputs, one from each classifier.
The other is less than twice the size of input layer. The number of hidden layers and hidden neurons per layer was taken arbitrarily. The number of hidden neuron depends on number of inputs, outputs, architectures, activations, training sets, algorithms, and noises. But be careful that too many neurons tend to cause overfitting. Short answer is: they don't. Concat layer comes under the hidden layer. In thump rule, is between size of number of input neurons and number of output neurons. However, I have found something in an article of Jeff Heaton that: and also found some rules about choosing the number of hidden neurons per layer: 1.
The neurons at the top of the image are from the output layer, the neurons below the output layer are from the hidden layer (top 12 neurons in terms of the distance between histograms). Suppose, there are two neurons in the input layer x1,x2 applied with their respective strengths called weights along with a bias b. Long answer now. In other words, there are 4 classifiers each created by a single layer perceptron.
The number of hidden neurons should be between the size of the input layer and the size of the output layer. The number of hidden neurons should be between the size of the input layer and the size of the output layer. Because the first hidden layer will have hidden layer neurons equal to the number of lines, the first hidden layer will have 4 neurons. The number of inputs to this layer; The number of neurons in this layer; The activation function to use; Our weights is a matrix whose number of rows is equal to the number of neurons in the layer, and number of columns is equal to the number of inputs to this layer. Based on my understanding, you can have any number of hidden neurons, no matter how many features you have.