Various architectures
Let's now take a look at some popular neural network architectures and their applications. We will start with multilayered perceptron (MLP) networks. We have already covered single-layered perceptron networks, which are the most basic neural network architectures.
MLPs and deep neural networks
MLP or simple deep neural networks (DNNs) are the most basic form of neural network architectures. The neural units are arranged layer after layer, and adjacent network layers are fully connected to one another. We have already discussed this in detail in the previous chapter:
Autoencoder neural networks
Autoencoders are typically used for reducing the dimensionality of data in neural networks. Autoencoders are also successfully used for anomaly detection and novelty detection problems. Autoencoder neural networks come under the unsupervised learning category. Here the target values are set to be equal to the inputs. In other words, we want to learn the identity function. By doing...
