Jordan Perr » intel http://jperr.com/wp A public display of my projects and thoughts. Mon, 23 Aug 2010 20:03:27 +0000 en hourly 1 http://wordpress.org/?v=3.0.1 Invited to NYCSEF final round! http://jperr.com/wp/post/271 http://jperr.com/wp/post/271#comments Thu, 11 Mar 2010 20:33:04 +0000 Jordan http://jperr.com/wp/?p=271 I just found out that my year long research project on the trends in Integrated Information in evolving neural networks has been accepted into the NYCSEF (New York City Science and Engineering Fair) final round at the Museum of Natural History.

The preliminary round took place last Sunday (3/7/10). This round included live, interrogation style judging by three separate judges. I am honored that they were impressed with my work.

A cell phone shot of me being interviewed by a student from S.I. Tech at NYCSEF.

]]> http://jperr.com/wp/post/271/feed 0 Intel Submission: Observing Integrated Information in Evolving Neural Networks http://jperr.com/wp/post/145 http://jperr.com/wp/post/145#comments Sun, 20 Dec 2009 11:04:59 +0000 Jordan http://jperr.com/wp/?p=145 I have completed a research paper on the how integrated information behaves during artificial evolution of neural networks in Polyworld. Mad props to Virgil Griffith (with his integrated information calculator) and Larry Yeager (author of the aforementioned Polyworld) for their incredible insight and willingness to help out a mere high school student.

Download the full paper as PDF (400k)

Abstract:

Evolution has proven to be a wildly successful autonomous process for creating intelligent systems in the natural world and in simulation. Since the early 1960s, re- searchers have used artificial evolution to find ingenious and novel solutions to complex problems such as series prediction and flight control. Recently, artificial evolution has been applied to neural networks with the aim of evolving more robust artificial intel- ligence. Several metrics have been proposed to chart the emergence of intelligence in these evolved networks. This work analyzes the behavior of a new metric, integrated information (φ). Observed data is analyzed, interpreted, and compared to more con- ventional properties of the artificial neural network. The data analysis shows that φ increases over evolutionary time and is therefore promising as a heuristic measure.

Experimental Data:

Results from Integrated Information experiments. The data set includes anatomical neural network sampled from 5,202 Polyworldians, at death, from three genetically independent simulations. Each data point represents a 200 time step bin size. *First sample for which p < 0.01

]]> http://jperr.com/wp/post/145/feed 0