[R] Review article/ textbook for optimizers and cost function for Neural Networks.

I am interested in learning in-depth about first order and second order optimizers. Also which optimizers is theoretical better for which cost function.

Would be helpful if it was related to convolution neural network or neural network, however for any machine learning is fine.

article convolution convolution neural network cost function machine machine learning machinelearning network networks neural network neural networks review textbook