For questions about a artificial networks, such as MLPs, CNNs, RNNs, LSTM, and GRU networks, their variants or any other AI system components that qualify as a neural networks in that they are, in part, inspired by biological neural networks.
Artificial networks include but are not limited to these and their variants.
- Multi-layer perceptrons (MLPs), a.k.a. feed forward networks
- Convolutional neural networks (CNNs)
- Recurrent neural networks (RNNs)
- Long short term memory (LSTM and B-LSTM) networks, types of RNNs
- Gated recurent unit (GRU) networks, type of RNN
- Recursive neural networks, an RNN
- Attention designs
- Spiking networks
These are often are called artificial neural networks (ANNs) because they are, in part, inspired by biological neural networks.
The most basic neural networks are used to estimate or approximate functions more complex than a first degree polynomial. In more sophisticated cases, they can be used in larger topologies to generate, analyze, or transform images, text, audio, and video.