Seminar: Understanding the Evolution of Cognition with Structural and Information-Theory Based A...
Seminar: Understanding the Evolution of Cognition with Structural and Information-Theory Based Analysis
Presenter: Clifford Bohm, Post-Doctoral Student at Michigan State University
Abstract: In this talk, I will present work on developing methods to better understand the structure of evolved digital cognitive architectures such as Markov Brain, RNN, and CGP. First, I will present Fragmentation, an information analysis that can be used to identify how data flows through cognitive architectures. Then I will discuss the Comparative Hybrid Approach, an empirical technique that can shed light on how the components of a given architecture may account for differences in performance between architectures.