Summary

In this chapter, we understood the need for a single network that performs both feature extraction and classification in a single shot, before we learned about the architecture and the various components of an artificial neural network. Next, we learned about how to connect the various layers of a network before implementing feedforward propagation to calculate the loss value corresponding to the current weights of the network. We next implemented backpropagation to learn about the way to optimize weights to minimize the loss value and learned how the learning rate plays a role in achieving optimal weights for a network. In addition, we implemented all the components of a network – feedforward propagation, activation functions, loss functions, the chain rule, and gradient descent to update weights in NumPy from scratch so that we have a solid foundation to build upon in the next chapters.

Now that we understand how a neural network works, we’ll implement one using PyTorch in the next chapter, and dive deep into the various other components (hyperparameters) that can be tweaked in a neural network in the third chapter.