I am very new to Machine learning and following the course offered by Andrew Ng. I am very confused How we train our neural network on Multi-class Classification(suppose take K classes). For K classes we will be training K different neural networks.
But Do we train one neural network at a time for all features or we train all K NN at a time for one feature? please explain the complete procedures.
Please help me with this. Consider that I have a very very basic understanding of neural networks in multi-class classification.