Discover the best answers to your questions with the help of IDNLearn.com. Join our community to receive prompt, thorough responses from knowledgeable experts.

Which of the following statements is true about the cost function used for training a neural network through the
gradient descent method?
- The cost function is never a differentiable function of the parameters of the network.
- The cost function is always a linear function of the parameters of the network.
- The cost function can have multiple local minima.
- The cost function is always a convex function of the parameters of the network