Slime Mold/Life Cycles
Self-copying Robot (2005)
Hod Lipson, Cornell
Programmable blocks
2 swiveling pyramidal
halves
Magnetic connections
10 cm across
One stack can
assemble another
Amoeba Stage
Single cell
Lives in soil
Free moving
Engulfs foo
Differentiation_
& Pattern Formation
A central problem in
development: How do cells
differentiate to fulfill
different purposes?
How do complex systems
generate spatial & temporal
structure?
CAs are natural models of
intercellular communication
Activat
II. Spatial Systems
A. Cellular Automata
Cellular Automata (CAs)
Invented by von Neumann in 1940s to study
reproduction
He succeeded in constructing a self-reproducing
CA
Have been used as:
massively parallel computer architecture
model of physical p
3/20/13
Project 4 - Backpropagation
Project 4 - Backpropagation
Data files
Each line of the file is one pattern which contains the input values x and y (and z) and the expected output value
as the last number in that line.
For Problem 1 (2 inputs)
trainin
4/13/13
Project 5 - Genetic Algorithms
Project 5 - Genetic Algorithms
Undergrad portion
The program should accept the following as input:
Number of genes (bits) in the genetic string l
Population size N
Number of generations G
Mutation probability pm
Cros
3/8/13
Project 3
CS 420/527 Project 3 Hopfield Net
Due March 8, 2013
General Description
In this project you will be investigating the associative memory capacity of a Hopfield
network. You will use N = 100 neurons with no self-coupling.
For additional in
3/8/13
Project 3 - Hopfield Net
Project 3 - Hopfield Net
Data structures
You will need a structure to hold the patterns (each with 100 neurons), a 50x100 array will work. A 100x100
array can be used to store the weights of the network. You will want to re
4/26/13
Project 6 - Particle Swarm Optimization
Project 6 - Particle Swarm Optimization
Parameters
The following is some guidance for the ranges of the parameters.
Number of particles: A typical range is 20-40. For many problems, as few as 10 particles ma
CS 420/527 Biologically Inspired Computation
Project 6
Due Monday, April 29, 2013
Implement the Particle Swarm Optimization (PSO) algorithm. Your program should take as arguments:
1. Number of epochs (iterations)
2. Number of particles
3. Inertia
4. Cogni
Trevor Sutch
4/15/2013
CS527
Project 5
Genetic Algorithms
Introduction
The language used for this project is Java. The goal of this project is to learn about genetic
algorithms, how they work and how changing parameters affects the results.
Discussion
The
CS 420/527 Spring 2013
Project 2
Creation of Spatial Structure
by Activator/Inhibitor Cellular Automaton
Due February 20, 2012
Background
Activator/Inhibitor Cellular Automaton
In this project you will investigate and measure the creation of spatial struc
CS 420/527: Biologically-Inspired Computation
Project 1: Edge of Chaos in 1D Cellular Automata
Due: Wednesday, Feb. 6, Midnight
Introduction
In this project you will explore Edge of Chaos phenomena (Wolfram class IV behavior)
in 1D cellular automata. You