Topic 2: Optimization Part-1

Empirical risk minimization, gradient descent, and stochastic gradient descent are three subtopic which we explain in this chapter.

In this section, we explain the chain rule of calculus, and it’s computational graphs.

This section introduces forward and backward passes, chain rule, and the details of backprop in deep learning.

We continue our discussion about backpropagation in formalism and recursion.

This section introduces GPU training for accelerated learning of neural networks, software for hardware support, and deep learning software platforms.