In
this article we discuss the types of artificial neural networks. These models simulate
the real life biological system of nervous system.
1. Feed forward
neural network:
- This is the simplest type of neural network that has been
ever devised.
- In these networks the information flow is unidirectional;
therefore the data moves only in forward direction.
- From input nodes data
flows to the output nodes via hidden nodes (if there are any).
- In this
model there are no loops or cycles.
- Different types of units can be used
for constructing feed forward networks for example, McCulloch – pitts
neurons.
- Continuous neurons are used in error back propagation along with
the sigmoidal activation.
2. Radial
basis function network:
- For interpolating in a multi – dimensional space
radial basis functions are the most powerful tools.
- These functions can be
built in to criterion of distance with respect to some center.
- These
functions can be applied in the neural networks.
- In these networks,
sigmoidal hidden layer transfer characteristic can be replaced by these
functions.
3. Kohonen
self–organization network:
- Un–supervised learning is performed with
the help of self – organizing map or SOM.
- This map was an invention of
Teuvo Kohonen.
- Few neurons learn mapping points in the input space that
could not coordinate in the output space.
- The dimensions and topology of
the input space can be different from those of the output space. SOM makes
an attempt for preserving these.
4. Learning
vector quantization or LVQ:
- This can also be considered as neural network
architecture.
- This one also was a suggestion of Teuvo Kohonen.
- In these prototypical representatives are
parameterized along with two important things namely, a classification
scheme based - up on distance and a distance measure.
5. Recurrent
neural network:
- These networks are somewhat contrary to the feed forward
networks.
- They offer a bi–directional flow of data.
- On a feed forward
network data is propagated linearly from input to output.
- Data from later
stages of processing is also transferred to its earlier stages by this
network.
- Sometimes these also double up as the general sequence
processors.
- Recurrent neural networks have a number of types as mentioned
below:
Ø
Fully recurrent network
Ø
Hopfield network
Ø
Boltzmann machine
Ø
Simple recurrent networks
Ø
Echo state network
Ø
Long short term memory network
Ø
Bi – directional RNN
Ø
Hierarchical RNN
Ø
Stochastic neural networks
6. Modular neural networks:
- As per the
studies have shown that human brain works actually as a collection of
several small networks rather than as just one huge network, this
ultimately helped in realizing the modular neural networks where smaller
networks cooperate in solving a problem.
- Modular networks are also of many
types such as:
Ø
Committee of machines: Different
networks that work together on a given problem are collectively termed as the
committee of machines. The result achieved through this kind of networking is
quite better than what is achieved with the others. The result is highly
stabilized.
Ø
Associative neural network or ASNN: This
is an extension of the previous one. And extends a little beyond the weighted
average of various models. This one is a combined form of the k- nearest
neighbor technique (kNN) and the feed forward neural networks. Its memory is
coincident with that of the training set.
7. Physical
neural network:
- It consists of some resistance material that is
electrically adjustable and capable of simulating the artificial synapses.
There
are other types of ANNs that do not fall in any of the above categories:
Ø
Holographic associative memory
Ø
Instantaneously trained networks
Ø
Spiking neural networks
Ø
Dynamic neural networks
Ø
Cascading neural networks
Ø
Neuro – fuzzy networks
Ø
Compositional pattern producing
networks
Ø
One – shot associative memory
