BUILDING AN ARTIFICIAL BRAIN

1
BUILDING AN ARTIFICIAL BRAIN

• Using an FPGA CAM-Brain Machine
• Mika Shoshani
• Yossy Salpeter

2
An ARTIFICIAL BRAIN?!

• What?
• A machine modeling the Human brain
• Why?
• Breaking the limits of traditional computers
• And How?
• Teaching the machine

3
Scope

• Introduction
• Background
• The basis of the Brain Building field
• The CAM-Brain machine
• Domo Arigato Mr. ROBOKONEKO
• Proof of concept
• Whats Next...

4
Buzz words

• Neurons, Axons, Dendrites
• Neural Network Module
• CAM - Cellular Automata Model
• FPGA - Field Programmable Gate Array
• Genetic Algorithms
• Evolvable Hardware

5
The Human Brain

• A network of 1014 neurons
• Data transfer by electric signals
• Dendrite cells (neurons Input)
• Collect signals and pass them to the neuron
• Neurons
• Decide when to initiate a signal
• Axon cells (neurons Output)
• Propagate neuron signals

6
Genetic Algorithms

• A process imitating natural evolution

Random population
Fitness function
REPRODUCTION
The fittest
New Generation
7
Genetic Algorithms

• A process imitating natural evolution

Random population
Fitness function
REPRODUCTION
The fittest
3ed Generation
8
Genetic Algorithms

• A process imitating natural evolution

Random population
Fitness function
REPRODUCTION
The fittest
4th Generation
9
Genetic Algorithms

• A process imitating natural evolution

Random population
Fittest individual
Fitness function
REPRODUCTION
The fittest
5th Generation
10
Evolvable Hardware

• The Application of a Genetic Algorithm on
  programmable hardware

Chip with random circuits
Functioning circuit
Measuring circuit
AT HARDWARE SPEEDS!!!
REPRODUCTION
Best Performing circuits
New Generation of mutant circuits
Evolve Hardware to perform a desired function
11
Human Brain vs. The Computer

• 1014 Neurons
• Parallel Computing
• Speed 100 M./sec.
• Natural Evolution

• CPU - Central Processing Unit
• Serial Computing
• Approx. Speed of light
• Designable

12
The CAM-Brain Machine (CBM)

• A research tool of an artificial brain
• Consists of 32,768 neural modules
• Neural modules evolve in hardware using Genetic
  Algorithms

13
CBM Goal

• Create a complex functionality without any a
  priori knowledge of how to achieve it

• Requires the desired Input/Output function!

14
CELLULAR automata MODEL

• A 3D grid of cells
• Each can be in one of a finite number of possible
  states.
• Sync. updated in discrete time steps.
• According to a local, identical interaction rule.

Chromosome
15
CBM Neural Network Model

• The CBM implements the
• CoDi Cellular Automata based
• neural network model
• Goals
• Fast evolution
• Portability into electronic hardware

16
CoDI Cell design

• A cube with six neighbor cells
• Can function as Neuron, Axon or Dendrite
• A Neuron Cell
• 5 dendritic inputs 1 axonic output
• 4-bit input accumulator, fires on threshold
• A Dendrite cell 5 Inputs / 1 Output
• An Axon cell 1 Input / 5 Outputs

17
CoDI Module Evolving

• All cells are seeded with chromosome
• Seed Neuron cells randomly
• Growth procedure
• Each Neuron sends grow dendrite/axon signals
• Blank cells become dendrite/axon
• Grown cells propagate growth signals
• Propagation direction is set by the chromosome

18
CoDI Module Evolving
19
CoDI Module evolution

• Each module is given a specific function
• Genetic Algorithem
• Initial population of 30-100 modules
• Run for 200-600 Generations
• Up to 60,000 different module evaluations
• Full module evolution takes approx. 1sec

20
CBM Architecture

• Cellular Automata Module
• Genotype/Phenotype Memory
• Fitness Evaluation Unit
• Genetic Algorithm Unit
• Module Interconnection Memory
• External Interface

21
Architecture 1

• Cellular Automata Module
• The hardware core of the CBM
• 3D array of identical logic circuits (cells)
• Module size of 242424 cells (13,824)
• Implemented by 72 FGPAs
• Time shared between multiple modules - Forming a
  brain during simulation.
• No idle time between modules

22
Architecture 2

• Genotype Phenotype Memory
• Total 1180 Mbytes RAM
• Genotype memory for Evolution mode
• Store Chromosome bitstrings
• Store module neuron location orientation
• Phenotype memory for Run mode
• Holds all evolved module maps
• Can support up to 32,758 modules

23
Architecture 3

• Fitness evaluation unit
• Evaluates module fitness
• Signals each module inputs
• Compares Module output to target output
• This comparison gives a measure of module
  performance

24
Architecture 4

• Genetic Algorithm Unit
• Selects a subset of the best evolved modules
  for reproduction
• Implements Crossover and Mutation masks
• Generates offspring modules
• Offspring chromosome generated in hardware

25
Architecture 5

• Module Interconnection Memory
• Supports operation of Evolved modules as one
  artificial brain
• Provides signaling between modules

26
Architecture 6

• External Interface
• CBM Signaling is by 1-bit spiketrains
• I/O For each module
• Input of up to 188 spiketrains
• Output of up to 3 spiketrains

27
Human Brain vs. CAM-Brain

• 1014 Neurons
• Parallel Computing
• Speed 100 M./sec.
• Natural Evolution

• 4107 Neurons
• 1150 parallel neurons
• Approx. speed of light
• Designable Evolution

28
ROBOKONEKO

• Political Strategic goals
• A controlled cat as a proof of concept
• Radio connected to CBM
• Demonstrates CBM via evolved behaviors
• Goal - The CUTE factor...

29
Behavior Evolving

• Moition control modules
• Fitness criterion - speed distance
• Mechanical vs. Simulated behavior evolving
• Slow evolution, 2-3 min. per chromosome
• Hand coded base criterion.
• Non motion control modules evolution -Predicted
  to be Faster

30
SUMMARY

• Artificial Brain Building
• CAM Brain Project
• Aims to build an artificial brain with 32000
  evolved net modules, 40 million neurons
• Robokoneko
• A Cat robot controled by the CAM-Brain
• In development of motion control modules

31
Whats Next...

• Intelligent robotic pets, Household robots,
  Soldier robots.
• Artilect - Artificial Intellect
• Ultra-Intelligent Artilect Moral dilemma

32
The prophecy

• Future WAR Cosmists vs. Terrans
• The End of Human race as we know it...

33
References 1

• "Building an Artificial Brain Using an FPGA Based
  CAM-Brain Machine", Applied Mathematics and
  Computation Journal, Special Issue on "Artificial
  Life and Robotics, Artificial Brain, Brain
  Computing and Brainware", North Holland. (Invited
  by Editor, to appear 1999), Hugo de Garis,
  Michael Korkin, Felix Gers, Eiji Nawa, Michael
  Hough.
• "A 40 Million Neuron Artificial Brain for an
  Adaptive Robot Kitten "Robokoneko", Hugo de
  Garis, Michael Korkin, Gary Fehr, Nikolai
  Petroff, Eiji Nawa, to be submitted to the
  Connection Science Journal, Special Issue on
  Adaptive Robots.
• "Simulation and Evolution of the Motions of a
  Life Sized Kitten Robot "Robokoneko" as
  Controlled by a 32000 Neural Net Module
  Artificial Brain", Hugo de Garis, Nikolai
  Petroff, Michael Korkin, Gary Fehr, Eiji Nawa,
  (Invitation by Editor to the Computational
  Geometry Journal (CGJ), Special Issue on
  Computational Geometry in Virtual Reality)

34
References www

• A Brief Introduction to Genetic Algorithms, by
  Moshe Sipper, http//lslsun.epfl.ch/moshes/ga_mai
  n.html
• Non-uniform cellular automata, by Moshe Sipper,
  http//lslsun.epfl.ch/moshes/ga_main.html
• Prof. Dr. Hugo de Garis Home Page,
  http//www.cs.usu.edu/degaris/
• CNN - Swiss scientists warn of robot Armageddon,
  http//www.cnn.com/TECH/science/9802/18/swiss.robo
  t/
• ??????????? ?????? ???????? - ????,
  http//gifted.snunit.k12.il/activities/brain/