Contents
- 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 2/3 the size of the input layer, plus the size of the output layer.
- The number of hidden neurons should be less than twice the size of the input layer.
How many nodes are needed in the input layer?
387 nodes
For your task: Input layer should contain 387 nodes for each of the features. Output layer should contain 3 nodes for each class.
How many neurons are in the hidden layer?
Because the first hidden layer will have hidden layer neurons equal to the number of lines, the first hidden layer will have four neurons. In other words, there are four classifiers each created by a single layer perceptron. At the current time, the network will generate four outputs, one from each classifier.
If the NN is a regressor, then the output layer has a single node. If the NN is a classifier, then it also has a single node unless softmax is used in which case the output layer has one node per class label in your model. So those few rules set the number of layers and size (neurons/layer) for both the input and output layers.
How to calculate number of layers and nodes in machine learning?
This can be a tough pill to swallow for beginners to the field of machine learning, looking for an analytical way to calculate the optimal number of layers and nodes, or easy rules of thumb to follow.
How many nodes are in an output layer?
Output layer should contain 3 nodes for each class. Hidden layers I find gradually decreasing the number with neurons within each layer works quite well ( this list of tips and tricks agrees with this when creating autoencoders for compression tasks).
Once hidden layers have been decided the next task is to choose the number of nodes in each hidden layer. The number of hidden neurons should be between the size of the input layer and the output layer. sqrt (input layer nodes * output layer nodes)