Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Introduction
Neurophysiological Background
Modeling Simplified Neurophysiological Information
The Hopfield Model
The Associative Memory Problem
The Model
Updating rules
One Pattern
Many Patterns
Stability of a particular pattern
Storage Capacity
The Energy Function
Discussion on Philosophy and Methodology
Artificial Neurons: Hopfield Networks
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Introduction
Inspiration
on today’s research in neural computation comes from
neuroscience
and is largely motivated by the possibility of
modeling artificial computing networks
.
So models are extremely
simplified
when seen from a neurophysiological point of view,
but one should gain insight in the behaviour of “biological” networks.
First the
neurophysiological background
should
be described:
information for modeling simplified
neurophysiological processes
description and the behaviour of
neural
networks
–
Hopfield Networks
.
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Neurophysiological Background
basic elements for a neural network:
neurons and their connections
Systematically the nervous system can be
divided into three parts

Input

central processing unit

output
In the field of
ANNs
, networks will be
constructed from neurons which have the
canonical division into an
input part
(dendritic arbor), a
processing part
(soma)
and a
signal transmission part
(axon).
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Modeling Simplified Neurophysiological Information (1)
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Modeling Simplified Neurophysiological Information (2)
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Modeling Simplified Neurophysiological Information (3)
This operation and its components leads to the basic formular
The operation can be expressed by the logical truth function
defines
variables
which are themselves zeros and ones
(which can also be considered as truth functions of some statement )
is a
function
which is 1 if the statement in the square brackets is true and is 0 otherwise
indicades, whether a spike (1 is sent) will appear in the output axon
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Modeling Simplified Neurophysiological Information (3)
A significant leap is acomplished, when the multi

neuron (
multi

perceptron
) is closed onto itself,
where the neurons form a
feedback mechanism
.
An ANN is no longer a linear, but a
dynamical
system, when output axons (signal transmission
parts) become input channels, there is a
time
shift
.
!
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Overview
Introduction
Neurophysiological Background
Modeling Simplified Neurophysiological Information
The Hopfield Model
The Associative Memory Problem
The Model
Updating rules
One Pattern
Many Patterns
Stability of a particular pattern
Storage Capacity
The Energy Function
Discussion on Philosophy and Methodology
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
The Hopfield Model

The Associative Memory Problem
Hopfield networks consist of the previously described elements and are totally
dynamical
,
so including the
time shift
and
possible updating rules
.
basic problem
:
to store a set of p patterns in such a way that when presented with
a new pattern , the network responds by producing whichever one
of the stored patterns most closely resembles
!
The space of all possible states of the network,
is called the
configuration space.
basins of attraction
:
Division of the the confirguration space by
stored patterns
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
The Model
The dynamics of the network can be represented by:
where
is represented for
with the conversion from =0 or 1 via =2

1
and sgn(x) is defined by:
The threshold terms can be dropped in consideration on random patterns being used.
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Updating rules

Two simplified versions
Synchronous or Parallel
All neurons update their activity states
simultaneously
at discrete time steps n,
where n = 1, 2, …, as if governed by a clock. The inputs of every neuron in the
network are determined by the same activity state of the network in the time interval
(n

1) < t < n.
This choice requires a
central clock
or pacemaker and is sensitive to
timing errors.
Asynchronous or Sequential
(
more natural for both brains and artificial networks)
All neurons are updated one by one, where one can proceed in either of two ways:
at each time step, select at random a unit
i
to be updated and apply the rule
let each unit independently choose to update itself, with some constant
probability per unit, according to
In this mode
:
every neuron coming up for a decision has full information about all
the decisions of the individual neurons that have been updated before it.
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
One Pattern
The condition for one pattern which should be memorized is
For constant of proportionality, using 1/N:
= 1/N
If fewer then half of the bits of the starting patterns are wrong they will be overwhelmed
in the sum for the net input
The network will correct errors and so the pattern is an attractor
All starting configurations with more than half the bits different
from the original pattern will end up in the reversed state

,
which leaves to a symmetrically divided configuration spaces into
two basins of attraction.
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Many Patterns
hypothesis made by Hebb (1949):
changes proportional to the correlation between the firing of the pre

and post

synaptic neurons
achieved through:
applying the set of patterns to the network during the training phase
adjust the strenghts according to such pre/post correlations
!
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Overview
Introduction
Neurophysiological Background
Modeling Simplified Neurophysiological Information
The Hopfield Model
The Associative Memory Problem
The Model
Updating rules
One Pattern
Many Patterns
Stability of a particular pattern
Storage Capacity
The Energy Function
Discussion on Philosophy and Methodology
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Stability of a particular pattern (1)
Going back to the condition for a stable one pattern
!
and the definiton of the net input
the stability condition generalizes to
Taking
the net input to unit in pattern
v
is
seperating the sum on into the special term
= v
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Stability of a particular pattern (2)
Meaning
!
crosstalk term
(is less than 1, in most cases)
If the second term were zero, one can conclude that pattern number
v
was stable according to
This is still true if the second term is small enough:
if its magnitude is smaller than 1 it cannot change the sign of
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
!
Storage Capacity
One consider the quantity by
The just depend on the patterns that one attempt to store
The distribution of values for the
crosstalkterm
For
p
random patterns and
N
units this is a Gaussian with
variance
The shaded area is ,
the probability of error per bit
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
The Energy Function (1)
… was atopted from a physical analogy to magnetic systems into the neural network
theory and is one of the most important contributions of the Hopfield paper.
One can imagine an
energy landscape metaphor
“above” the configuration space
with a multi

dimensional surface with hills and valleys.
The energy function is
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
The Energy Function (2)
central property
:
It is a function that always decreases (or remains constant) as the system evolves
according to its dynamical rule.
The attractors are at local minima (the valleys) of the energy surface, the dynamics then
can be thought of as similar to the motion of a partical on the energy surface under the
influence of gravity (pulling it down) and friction (so that it does not overshoot).
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
The Energy Function (3)
alternate derivation of the
Hebb prescription
(as we know it from the many pattern case)
minimized when the overlap between network configuration and the stored pattern
(
one pattern case
) is largest.
using:
analog:
many

pattern case:
patterns should be made into local minima of H
!
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
The Energy Function (4)
Multplying
out
out leads to the original energy function
!
good approach of finding the appropriate connection strength , by finding an energy
function whose minimum satisfies a problem of interest, and by multiplying it out
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
The Energy Function (5)
“Simple and nice”
proving of the central property of the Energy Function
!
It is a function that always decreases (or remains constant) as the system
evolves according to its dynamical rule.
energy function for the t state
energy function for the t+1 state
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Discussion on Philosophy and Methodology (1)
Research in these particular areas involves many different fields of science:

Biology

chemistry

physics

(...)
natural phenomena are described by
mathematical models
, sometimes being interpreted
that all natural phenomena are
reducible
to physical laws.
Alternatively

as I would say too

reduction can be given a very intuitive sense in which it
not only exists but is extremely useful and productive.
Hopflied once stated that
“the brain is a physical system”,
which may indeed sound like a
call for a
reduction of thought process
, nevertheless concepts originating in physics can
be used as analogues, including energy, field, relaxation etc.
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Discussion on Philosophy and Methodology (2)
The theory of attractor neural networks (ANN) has engaged in providing a minimal amount of
propositions which can be confronted with
experiment
.
This matter plays a role in discussing the attitude to
verification and/or falsification
and
the fact that a theoratical framework must be fended off by an explanation.
In many instances systems have been constructed
(hardware implemantations
/
computer simulations)
, being experimental setups for described models and providing a
truly impressive agreement on predicitions by the analysis of the models
But
this will not please no experimenter who records, using ingeniuos techniques, the
electrical activities in the cortex of cats or monkeys, for example.
For the future:
the theory of neural networks is to produce models, about
cognitive
processes
and which should be robust to the type of
disorder, fluctuations, disruptions
one can imagine the brain to be operating under.
Including:
parallel processing
or
potential for abstraction
!
Artificial Neurons: Hopfield Networks
Seminar:
Introduction to the Theory of Neural Computation
Discussion on Philosophy and Methodology (3)
So
what
happenes
if
a
experiment
may
not
show
the
type
of
bahaviour
identified
as
the
emergent
dynamics
.
Interpretion
:
a
refutation
of
the
theoretical
construction
or
arguing
that
the
experiment
has
missed
the
theory
.
Thank you very much!
Feel free to ask questions!
!
Comments 0
Log in to post a comment