Artificial neural networks in a nutshell by examples

Systems Biology and Computational Intelligence

on this manuscript, we report the proposal of the use of computational intelligence methods as a powerful and valuable source of mathematical tools for modeling gene expression networks. Gene expression networks are modeled via transcription networks. Transcription networks are graphoriented mathematical-computational models that attempt to understand gene expression as simpler and smaller systems named network motifs. Each type of transcription network presents a peculiar set of network motifs. Those models of gene expression are part of a bigger scientific field titled in the current state of the art as Systems Biology; which does not look upon individual genes, but plenty of them simultaneously. On the other hand, neural networks are graph-oriented mathematical models with roots on philosophy, physiology, neuroscience, physics, computer science and other scientific branches and they have been promising as mathematical models for modeling

nonparametric data and systems with hidden laws; they are interesting models for mapping spaces of relative high dimensional existence.

Go on: ResearchGate (Full PDF)

Associative memory

In summary, the Hopfield networks are an intelligent self-content addressable system. It recovers bad input based on previous experience, introduced on the system on the training phase. Hopfield network is based on our capability to recognize objects even under noisy environment.