Transcript Slide 1

An Overview of Core CI Technologies
Lyndon While
An Overview of Core CI Technologies
CITS7212: Computational Intelligence
Evolutionary Algorithms (EAs)
Reading:
X. Yao, “Evolutionary computation: a gentle introduction”, Evolutionary
Optimization, 2002
T. Bäck, U. Hammel, and H.-P. Schwefel, “Evolutionary computation:
comments on the history and current state”, IEEE Transactions on Evolutionary
Computation 1(1), 1997
An Overview of Core CI Technologies
CITS7212: Computational Intelligence
The Nature-Inspired Metaphor
Inspired by Darwinian natural selection:
– population of individuals exists in some environment
– competition for limited resources creates selection
pressure: the fitter individuals that are better adapted to
the environment are rewarded more than the less fit
– fitter individuals act as parents for the next generation
– offspring inherit properties of their parents via genetic
inheritance, typically sexually through crossover with
some (small) differences (mutation)
– over time, natural selection drives an increase in fitness
EAs are population-based “generate-and-test”
stochastic search algorithms
An Overview of Core CI Technologies
CITS7212: Computational Intelligence
2
Terminology
Gene: the basic heredity unit in
the representation of individuals
Genotype: the entire genetic makeup of an
individual – the set of genes it possess
Phenotype: the physical manifestation
of the genotype in the environment
Fitness: evaluation of the phenotype
at solving the problem of interest
Evolution occurs in genotype space based
on fitness performance in phenotype space
An Overview of Core CI Technologies
CITS7212: Computational Intelligence
5
3
The Evolutionary Cycle
Parent selection
Parents
Initialisation
Population
Genetic variation
(mutation and
recombination)
Termination
Survivor selection
An Overview of Core CI Technologies
Offspring
CITS7212: Computational Intelligence
4
An Example
X X
5
6
An Overview of Core CI Technologies
4
8
2
5
CITS7212: Computational Intelligence
5
EA Variants
There are many different EA variants/flavours:
– differences are mainly cosmetic and often irrelevant
– the similarities dominate the differences
Variations differ predominately on representation:
–
–
–
–
genetic algorithms (GAs): binary strings
evolution strategies (ESs): real-valued vectors
genetic programming (GP): expression trees
evolutionary programming (EP): finite state machines
and also on their historical origins/aims, and
their emphasis on different variation operators
and selection schemes
An Overview of Core CI Technologies
CITS7212: Computational Intelligence
6
Designing an EA
Best approach for designing an EA:
– choose a representation to suit the problem, ensuring
(all) interesting solutions can be represented
– create a fitness function with a useful search gradient
– choose variation operators to suit the representation,
being mindful of any search bias
– choose selection operators to ensure efficiency while
avoiding premature convergence to local optima
– tune parameters and operators to the specific problem
Need to balance exploration and exploitation:
– variation operations create diversity and novelty
– selection rewards quality and decreases diversity
An Overview of Core CI Technologies
CITS7212: Computational Intelligence
7
Neural Networks (NNs)
Reading:
S. Russell and P. Norvig, Section 20.5, Artificial Intelligence: A Modern
Approach, Prentice Hall, 2002
G. McNeil and D. Anderson, “Artificial Neural Networks Technology”, The Data
& Analysis Center for Software Technical Report, 1992
An Overview of Core CI Technologies
CITS7212: Computational Intelligence
The Nature-Inspired Metaphor
Inspired by the brain:
– neurons are structurally
simple cells that aggregate
and disseminate electrical
signals
– computational power and
intelligence emerges from
the vast interconnected
network of neurons
NNs act as function
approximators or pattern
recognisers which learn
from observed data
An Overview of Core CI Technologies
Diagrams taken from a report on neural
networks by C. Stergiou and D. Siganos
CITS7212: Computational Intelligence
9
The Neuron Model
A neuron combines
values via its input and
activation functions
The bias determines the
threshold needed for a
“positive” response
Single-layer neural
networks (perceptrons)
can represent only
linearly-separable
functions
An Overview of Core CI Technologies
Bias Weight
a 0  1
W
Activation
Function
0, i
g
aj
W j, i
Input
Links

Input
Function
ai
Output
Output
Links
 n

ai  g   W j, i  aj 


 j0

CITS7212: Computational Intelligence
10
Multi-Layered Neural Networks
A network is formed by
the connections (links) of
many nodes – inputs to
outputs through one or
more hidden layers
Link weights control the
behaviour of the function
represented by the NN
– adjusting the weights
changes the encoded
function
An Overview of Core CI Technologies
CITS7212: Computational Intelligence
11
Multi-Layered Neural Networks
Hidden layers increase the “power” of the NN at
the cost of extra complexity and training time:
– perceptrons capture only linearly-separable functions
– an NN with a single (sufficiently large) hidden layer can
represent any continuous function with arbitrary accuracy
– two hidden layers are needed to represent
discontinuous functions
There are two main types of multi-layered NNs:
1. feed-forward: simple acyclic structure – the stateless
encoding allows functions of just its current input
2. recurrent: cyclic feedback loops are allowed – the
stateful encoding supports short-term memory
An Overview of Core CI Technologies
CITS7212: Computational Intelligence
12
Training Neural Networks
Training means adjusting link weights to minimise
some measure of error (the cost function)
– i.e. learning is an optimisation search in weight space
Any search algorithm can be used, most commonly
gradient descent (back propagation)
Common learning paradigms:
1. supervised learning: training is by comparison with
known input/output examples (a training set)
2. unsupervised learning: no a priori training set is
provided; the system discovers patterns in the input
3. reinforcement learning: training uses environmental
feedback to assess the quality of actions
An Overview of Core CI Technologies
CITS7212: Computational Intelligence
13
Questions?
An Overview of Core CI Technologies
CITS7212: Computational Intelligence