What are different types of Artificial Neural Networks?¶
1.Feedforward Neural Network: Neural Network that the cells do not form a cycle.
1.1.Multilayer Perceptron: Feedforward Neural Network with perceptrons organized into input, hidden and output layers.
1.1.1.Convolutional Neural Network: Multilayer Perceptron with convolutional layers.
1.2.Autoencoder: Feedforward Neural Network with equal number of inputs and outputs trained to replicate the input.
2.Recurrent Neural Network: Neural Network that have access to their output from previous time steps.
2.1.LSTM Recurrent Neural Network: Long Short Term Recurrent Neural Networks are Recurrent Neural Networks with LSTM cells with memory.
2.2.GRU Recurrent Neural Network: Gated Recurrent Unit Neural Networks are Recurrent Neural Networks with GRU cells.
2.3.Neural Turing Machine: Recurrent Neural Network with neural network controller coupled to external memory.
3.Transformer: Neural Network with a structure of encoder and/or decoder with presence of attention mechanism that is predominantly used in Natural Language Processing.
4.Stochastic Neural Network: Neural Network with random variations introduced to the network via stochastic transfer functions or stochastic weights.
4.1.Restricted Boltzman Machine: Neural Network consisting of input and hidden cells trained to learn the probability distribution of its set of inputs.
4.2.Deep Belief Network: Neural Network consisting of stacking of Restricted Boltzman Machines and their training in a greedy manner.
5.Generative Adverserial Networks: Combination of a generative network and a discriminative network in a competing training.