# Neural Network Designs¶

## 1.Feedforward Neural Network¶

Neural Network that the cells do not form a cycle.

### 1.1.Multilayer Perceptron¶

Feedforwrd Neural Network with perceptrons organized into input, hidden and output 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 the cells form a directed graph.

### 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.Stochastic Neural Networks¶

Neural Network with random variations introduced to the network via stochastic transfer functions or stochastic weights.

### 3.1.Restricted Boltzman Machine¶

Neural Network consisting of input and hidden cells trained to learn the probability distribution of its set of inputs.

### 3.2.Deep Belief Network¶

Neural Network consisting of stacking of Restricted Boltzman Machines and their training in a greedy manner.

## 4.Generative Adverserial Networks¶

Combination of a generative network and a discriminative network in a competing training.