Neural networks algorithms take inspiration from the brain and involve large numers of simple neurons all working together. They are typically organised in layers where the outputs of one layer of neurons form the input to the next, but some neural networks, including Boltzmann machine and Kohonan networks, have connections within layers. Many neural networks are trained using some form of backpropagation.
Used in Chap. 1: pages 3, 6; Chap. 2: page 19; Chap. 3: page 33; Chap. 7: pages 92, 96, 99; Chap. 8: pages 102, 105, 115; Chap. 9: pages 117, 118, 120, 121, 122, 123, 127; Chap. 10: pages 139, 140; Chap. 11: pages 147, 148, 157, 159; Chap. 12: pages 162, 177, 180, 181, 182, 186, 187; Chap. 13: page 202; Chap. 14: pages 204, 212, 213, 217, 219, 220; Chap. 15: page 234; Chap. 16: pages 242, 247; Chap. 18: pages 272, 280, 283, 288; Chap. 19: pages 293, 303, 305, 309; Chap. 20: pages 324, 325; Chap. 21: pages 330, 335, 337, 339; Chap. 22: pages 343, 346, 347, 349; Chap. 23: pages 361, 366
Also known as neural net
A multi-layer perceptron architecture
Deep learning architecture – multiple layers, with varying connection topologies.
Boltzmann Machine – fully conneced between and withi layers