Artificial neural network
computational model used in machine learning, based on connected, hierarchical functions | |||||
Upload media | |||||
Spoken text audio | |||||
---|---|---|---|---|---|
Pronunciation audio | |||||
Instance of |
| ||||
Subclass of |
| ||||
Facet of | |||||
Has part(s) |
| ||||
| |||||
![]() |
Structure
Neurons in artificial neural networks are generally structured in layers, each layer holding several neurons. This structure can be quite different.
Three different structures are shown here:
- Neural network with one layer (without description).
- Neural network with one layer (english description).
- Neural network with one layer (German description).
- Neural network with two layers (english description).
- Neural network with one recurrent layer (without description).
- Neural network with one recurrent layer (english description).
- Neural network with one recurrent layer (German description).
- Threshold outsourced as a bias neuron.
Neuron
A artificial neural network is build from several Neurons. A Neuron can be drawn in the following way:
- Artificial neuron (without description).
- Artificial neuron (english description).
- Artificial neuron (German description).
- Artificial neuron (French description).
- Artificial neuron (without description).
Activation functions
Neurons can have different activation functions.
Three different functions are described here:
Hard limit function
A neuron with a hard limit function
Piecewise linear function
Sigmoid function
A sigmoid function is also called a McCulloch-Pitts Model. can have a variable slope parameter
- Hard limit activation function.
- Piecewise linear activation function.
- Sigmoid function with slope .
- Radial base activation function.
- Hyperbolic tangens activation function.
Specific types
Recurrent neural networks
- Recurrent neural network (RNN) and its unfold version
- A diagram for a one-unit Long Short-Term Memory (LSTM)
- A diagram for a one-unit Gated Recurrent Unit (GRU)
Elman Networks
Elman Networks are special artificial neural networks which have a memory and thus are able to represent time in an implicit way.
- Elman Network without description.
- Elman Network with english description.
- Elman Network with german description.
Time Delay Neural Networks
Time Delay Neural Networks (TDNNs) are special artificial neural networks which receive input over several time steps. Time is represented in an explicit way. The image shows an two-layer TDNN with neuron activations.
- TDNN without description.
- TDNN with english description.
- TDNN with german description.