Search the Mindcreators site:

1.0 Introduction

1. Website Purpose

I built this website to document the progress on my research into machine intelligence. Specifically, I am currently focused on building a computer simulation that behaves like a common, everyday insect using neural networks. Most researchers in the field of Artificial Intelligence (AI) try to understand and replicate human thought and abilities. I believe this is a mistake. You must start small and work your way up the evolutionary ladder, not immediately start with the most complicated thing in the known universe. Insects seem pretty stupid when compared with humans, but they are capable of a variety of intelligent, adaptive behaviors in a very unpredictable environment. And that is something that no man made system is yet capable of emulating. Also, when you get groups of insects working together in a cooperative manner they are capable of almost miraculous accomplishments. Once we begin to understand how these tiny brains work to produce such incredible behaviors then we will be able to harness that power for useful purposes.

I thought I would start by giving you a small look at what is contained in this website. The first project I built independently reproduces work originally done by Dr. Randall Beer of Case Western Reserve University in computational neuroethology. The second project is original work of mine to create a developmental neurobiology simulation system. This simulator will take digital chromosomes and use them to grow neural networks using the principles of developmental biology.

2. Insect Simulator

Update Alert!

I have now finished work on a much more advanced version of the insect simulator named AnimatLab. AnimatLab is a software tool that combines biomechanical simulation and biologically realistic neural networks. You can build the body of an animal, robot, or other machine and place it in a virtual 3-D world where the physics of its interaction with the environment are accurate and realistic. You can then design a nervous system that controls the behavior of the body in the environment. The software currently has support for simple firing rate neuron models and leaky integrate and fire spiking neural models. In addition, there a number of different synapse model types that can be used to connect the various neural models to produce your nervous system. On the biomechanics side there is support for a variety of different rigid body types, including custom meshes that can be made to match skeletal structures exactly. The biomechanics system also has hill-based muscle and muscle spindle models. These muscle models allow the nervous system to produce movements around joints. In addition, there are also motorized joints for those interested in controlling robots or other biomimetic machines. This allows the user to generate incredibly complicated artificial lifeforms that are based on real biological systems. Best of all AnimatLab is completely free and it includes free C++ source code!

The insect simulator uses knowledge of how real cockroach brains are wired to build artificial neural networks that produce similar behaviors in virtual insects. This video shows a simulated insect in a virtual environment with some food. The red objects are obstacles, and the green blocks are food that give off odors. The example insect displays several adaptive behaviors that are usually only associated with real organisms.

Sample Insect Simulation

Video 1. Simulation Example. Video Size: 1.5 Mb

However, The important thing to realize about this example is that nowhere did I explicitly program any of this behavior into the simulation. Every action, every movement and behavior of this simulated insect is completely controlled by its neural network brain. Sensory neurons detect things like the rotation of the legs and the chemical odors from food. The neurons in the brain then take these sensory perceptions and produce behavior. That behavior controls the motor neurons which move the legs and mouth allowing the insect to walk and eat. Even more incredible is that all of these complex behaviors are brought about with less than two hundred neurons.

3. Developmental Simulator

Achaete Scute Lateral Inhibition Example

Video 2. This video demonstrates the achaete scute lateral inhibition gene system. In this example all cells begin with the same initial values of transcription factors. Video Size: 847 Kb

This project uses the principles of developmental biology in an attempt to actually grow a virtual brain. The growth of the neural network is completely controlled by a digital chromosome. However, this is just the first phase of this project, and it still has a long way to go before it can grow a functioning network. The above video shows the achete scute lateral inhibition gene system. This is a well known model in developmental biology where one cell expresses certain proteins that in turn inhibits its neighboring cells from expressing those same proteins. This example is explained in detail in the results section. A number of other examples are also shown including the formation of a grid, and the dorso-ventral patterning of drosophila.

4. What's Ahead

I hope that this has been enough to wet your appetite to learn more. This document is broken up into several sections, and I will be adding more as I progress farther in my goals. Here is a list of the current topics discussed on this site. Section four is the one that goes into details of how the insect simulator works, and section five discusses the current work done on the developmental simulator. If you are specifically interested in one of these then feel free to skip directly to them.