Discover & eXplore Neural Network (DXNN) Platform, a Modular TWEANN

08/14/2010
by   Gene I. Sher, et al.
0

In this paper I present a novel type of Topology and Weight Evolving Artificial Neural Network (TWEANN) system called Modular Discover & eXplore Neural Network (DXNN). Modular DXNN utilizes a hierarchical/modular topology which allows for highly scalable and dynamically granular systems to evolve. Among the novel features discussed in this paper is a simple and database friendly encoding for hierarchical/modular NNs, a new selection method aimed at producing highly compact and fit individuals within the population, a "Targeted Tunning" system aimed at alleviating the curse of dimensionality, and a two phase based neuroevolutionary approach which yields high population diversity and removes the need for speciation algorithms. I will discuss DXNN's mutation operators which are aimed at improving its efficiency, expandability, and capabilities through a built in feature selection method that allows for the evolved system to expand, discover, and explore new sensors and actuators. Finally I will compare DXNN platform to other state of the art TWEANNs on a control task to demonstrate its superior ability to produce highly compact solutions faster than its competitors.

READ FULL TEXT
research
11/28/2010

DXNN Platform: The Shedding of Biological Inefficiencies

This paper introduces a novel type of memetic algorithm based Topology a...
research
01/28/2023

Composing Task Knowledge with Modular Successor Feature Approximators

Recently, the Successor Features and Generalized Policy Improvement (SF ...
research
07/27/2017

Modular AWG-based Optical Shuffle Network

This paper proposes an arrayed-waveguide grating (AWG) based wavelength-...
research
04/16/2021

ALF – A Fitness-Based Artificial Life Form for Evolving Large-Scale Neural Networks

Machine Learning (ML) is becoming increasingly important in daily life. ...
research
01/30/2017

PathNet: Evolution Channels Gradient Descent in Super Neural Networks

For artificial general intelligence (AGI) it would be efficient if multi...
research
11/25/2011

Evolving Chart Pattern Sensitive Neural Network Based Forex Trading Agents

Though machine learning has been applied to the foreign exchange market ...
research
05/21/2021

On the use of feature-maps and parameter control for improved quality-diversity meta-evolution

In Quality-Diversity (QD) algorithms, which evolve a behaviourally diver...

Please sign up or login with your details

Forgot password? Click here to reset