How can I make a Neural Network with graphical inputs?

1 visualización (últimos 30 días)
Joao Cardoso
Joao Cardoso el 30 de Jun. de 2015
Editada: Joao Cardoso el 30 de Jun. de 2015
Hello everyone, first of all, I wanted to say that I am beginner using MATLAB and Neural Networks app, only knowing the basics. I am currently a researcher in biotechnology currently trying to diminish the costs of new-generation drugs.
I wanted to ask if it's possible using a Supervised Neural Network with graphical inputs. For example, I have 100 graphs resulting of a specific mouse behavior (depressed mouse for instance), and in the other hand I have more 100 graphs resulting from a happy mice.
With an unknown behaviour curve I want the percentage of "similarity" with the happy mice curves and depressed ones. Similar to what we get with the Breast Cancer and Wine Vintage pre-defined datasets that come with the app, but with the major difference of the graphical inputs instead of the normalized value per class.
Many thanks in advance,
Note 1: I have the curves in an excel and each one has more than 20 000 dots. Note 2: I do not actualy work with mice, and used that example to simplify the question only. My curves are time vs energy, and my outputs are Ionic Exchange behavior and Hydrophobic interaction behavior.

Respuestas (0)

Categorías

Más información sobre Sequence and Numeric Feature Data Workflows en Help Center y File Exchange.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by