Toying Around With Neural Networks

Dreaming Lucidly

Neural networks have been around in one form or another for millions of years.

Up until fairly recently (from 1940 onward) they were only implemented in wetware inside of various living organisms.  In recent decades it has become possible to implement neural networks on hardware and software to great effect in areas like speech recognition and computer vision.

There are many types of neural networks.  The feedforward neural network has been extensively studied and is often used to provide an introduction to the concepts underlying neural network technology.   The diagram below shows how an equation from introductory algebra can be interpreted as  a feedforward  neural network.

2-Layer NN Backprop Article Lin Eq Diagram

The feedforward neural network has “units” (the circles) that perform mathematical operations on the sum of outputs from connected units multiplied by the “weight” (the boxes) on the connection. The unit at the very end of the processing stream is the output unit which…

View original post 2,988 more words

About fdnropsec

I have earned a Bachelor of Science in International Relations from the University of Houston where I also minored in International Business and Print Journalism. During my time in the journalism field I had the unique opportunity to meet and interview President George W. Bush and former Defense Secretary Robert Gates during the lead up to the Iraq war. Since then my studies have focused on predictive analytics in the areas of nuclear counter-terrorism, criminal intelligence analysis and foreign policy analysis in a freelance capacity. Currently, I am pursuing a Master of Arts in Intelligence Studies at American Military University. I am a contributing member of the Academy of Political Science, member of the National Military Intelligence Association, and am an International Gold Key Scholar. That said, I have designed this collective analytical effort to operationalize and fuse various analytic frameworks so as to generate a predictive model that will mitigate cognitive bias, frivolous speculation, and nonsensical character assaults, and ultimately deliver comprehensive quantifiable OSINT products containing sound and transparent analytic judgments to the search for Dylan Redwine deliverable through a custom Geographic Information System (GIS).

Posted on March 11, 2013, in Uncategorized. Bookmark the permalink. Leave a comment.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: