- What does output z_2 2 3 represent according to the notation defined for DNN?
- Why do we need multiple layers in deep learning?
- How many layers should a deep neural network have?
What does output z_2 2 3 represent according to the notation defined for DNN?
What does outputz_2^[2](3)z2[2](3)represent according to thenotation defined for DNN? A:activated output of 3rd node in second layer for second training sample X.
Why do we need multiple layers in deep learning?
Basically, by adding more hidden layers / more neurons per layer you add more parameters to the model. Hence you allow the model to fit more complex functions.
How many layers should a deep neural network have?
If data is less complex and is having fewer dimensions or features then neural networks with 1 to 2 hidden layers would work. If data is having large dimensions or features then to get an optimum solution, 3 to 5 hidden layers can be used.