Many machine learning libraries have an API for creating and working with neural networks. All the libraries we used in the previous chapters—Shogun, Dlib, and Shark-ML—are supported by neural networks. But there are also specialized frameworks for neural networks; for example, one popular one is the PyTorch framework. The difference between a specialized library and the common purpose libraries is that the specialized one supports more configurable options and supports different network types, layers, and loss functions. Also, specialized libraries usually have more modern instruments, and these instruments are introduced to their APIs more quickly.

In this section, we'll create a simple MLP for a regression task with the Shogun, Dlib, and Shark-ML libraries. We'll also use the PyTorch C++ API to create a more advanced network—a convolutional deep neural network with the LeNet5 architecture, which we discussed earlier in the Convolution network architecture section. We'll use this network for the image classification task.