Mastering Python for Finance - Second Edition

Network architecture

The network architecture of a neural network defines its behavior. There are many forms of network architecture available; some are:

• Perceptron (P)
• Feed forward (FF)
• Deep feed forward (DFF)
• Radial basis function network (RBF)
• Recurrent neural network (RNN)
• Long/short-term memory (LSTM)
• Autoencoder (AE)
• Hopfield network (HN)
• Boltzmann machine (BM)
• Generative adversarial network (GAN)

The most well-known and easy-to-understand neural network is the feed forward multilayer neural network. It can represent any function using an input layer, one or more hidden layers, and a single output layer. A list of neural networks can be found at http://www.asimovinstitute.org/neural-network-zoo/.