My problem has 3 classes.
I want to implement a single neural network, which has only one neural at the output layer, to classify these 3 classes.
Is there any way to implement it?
artificial intelligenceclassificationmachine learningneural networks
My problem has 3 classes.
I want to implement a single neural network, which has only one neural at the output layer, to classify these 3 classes.
Is there any way to implement it?
Best Answer
If your problem is truly classification you shouldn't implement output as one neuron, since you add strong a prior assumption about your class correlation. You can use one neuron only for binary class problems. Use 3 neurons outputs for 3-class problems. Check this example https://janakiev.com/notebooks/keras-iris/