Short View:
Neural Networks have been applied
widely to real problem modeling. The applications have been concentrated mainly
on image processing, classification of patterns, and function approximation.
The best characteristic of neural networks from the point of view for function
approximation is the parallel processing power. Besides neural networks by its
own are just linear models, their local structure for calculation, named
neurons, may be selected properly in order to those behave as a nonlinear
model. In the other hand, Transcription Networks has been applied as a gene
expression modeling tool. The principle behind those is that nature solves
problems in “local machines” termed network motifs. Here is claimed that the
theory of neural networks is a powerful tool for transcription network modeling
based on experimental data from gene expression.
All the living
organism physical state is function in a production and replication level of
the genetic code, including all the biological fluids and internal structures.
One may use applied genetics to explain biological components, such as the
blood cells or different biological liquid separators, which in wrong
development or repairing processing may be the cause of significant physical
diseases. This justifies the study of genetics in the gene-level.
Key-words: Neural Networks;
Transcription Networks; Gene Expression Estimation; Systems Biology.
 |
| Schematic view of how a typical supervised neural network handles the data for learning |
 |
| Schematic view of the backpropagation, two waves of information, backward and forward |
 |
| Typical challenges faced in neural network design |
No comments:
Post a Comment