1 financial informatics –xiv: basic principles 1 khurshid ahmad, professor of computer science,...

35
1 Financial Informatics – XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2, IRELAND November 19 th , 2008.

Upload: brianne-weaver

Post on 31-Dec-2015

222 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

1

Financial Informatics –XIV:Basic Principles

1

Khurshid Ahmad, Professor of Computer Science,

Department of Computer Science

Trinity College,Dublin-2, IRELAND

November 19th, 2008.https://www.cs.tcd.ie/Khurshid.Ahmad/Teaching.html

Page 2: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

2

Neural Networks

Artificial Neural Networks The basic premise of the course, Neural Networks, is to introduce our students to an alternative paradigm of building information systems.

Page 3: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

3

Artificial Neural Networks

An ANN system can be characterised by  

•its ability to learn;•its dynamic capability;

and • its interconnectivity

Page 4: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

4

  Artificial Neural Networks:

An Operational View

Input S

ignals yk

Output

Signal

wk3

wk1

wk2

wk4

Neuron xk

x1

x2

x3

x4

bk

Summing Junction

Activation Function

)(

)(0

****

:

1

1

1

44332211

THRESHOLDnetifnety

THRESHOLDnetify

functionidentitynegativenon

netyfunctionidentity

outputNeuronal

xwxwxwxwnet

sumweightedorinputNet

Page 5: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

5

  Artificial Neural Networks:

An Operational View A neuron is an information processing unit forming the key ingredient of a

neural network: The diagram above is a model of a biological neuron. There are three key ingredients of this neuron labelled xk which is connected to the (rest of the) neurons in the network labelled

x1, x2, x3,…xj.

A set of links, the biological equivalent of synapses, which the kth neuron has with the (rest of the) neurons in the network. Note that each link has a WEIGHT denoted by labelled

wk1, wk2,…wkj, where the first subscript (k in this case) denotes the recipient neurons and

the second subscript (1,2,3…..j) denotes the neurons transmitting to the recipient neurons. The synaptic weight wkj may lie in a range that includes negative (inhibitory) values and positive (excitatory) values.

(From Haykin 1999:10-12)

Page 6: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

6

  Artificial Neural Networks:

An Operational View

The kth neuron adds up the inputs of all the transmitting neurons at the summing junction or the adder, denoted by . The adder acts as a linear combiner and generates a weighted average usually denoted by uk:

uk = wk1i*x1 + wk2*x2 + wk3*x3 + ………. + wkj*xj;

the bias (bk )has the effect of increasing or decreasing the net input to the activation function depending on the value of the bias.(From Haykin 1999:10-12)

(From Haykin 1999:10-12)

Page 7: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

7

 ANN’s: an Operational View

Finally, the linear combination, denoted as vk = uk + bk, is passed through the activation function which engenders the non-linear behaviour seen in the behaviour of the biological neurons: the inputs to and outputs from a given neuron show a complex, often non-linear behaviour. For example, if the output from the adder was positive or zero then the neuron will emit a signal,

yk = 1 if (vk)0 , however if the output from the adder was negative then there will be no output,

yk = 0 if (vk)< 0 .

There are other models of the activiation function as we will see later.

(From Haykin 1999:10-12)

Page 8: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

8

 ANN’s: an Operational View

Input S

ignals yk

Output

Signal

wk3

wk1

wk2

wk4

Neuron xk

x1

x2

x3

x4

bk

Summing Junction

Activation Function

)(

)(0

tan

****

:

1

1

1

44332211

THRESHOLDnetifCy

THRESHOLDnetify

netytcons

outputNeuronal

xwxwxwxwnet

sumweightedorinputNet

Page 9: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

9

 ANN’s: an Operational View

Input S

ignals yk

Output

Signal

wk3

wk1

wk2

wk4

Neuron xk

x1

x2

x3

x4

bk

Summing Junction

Activation Function

)(1

)(0

****

:

1

1

44332211

THRESHOLDnetify

THRESHOLDnetify

outputSaturated

outputNeuronal

xwxwxwxwnet

sumweightedorinputNet

Page 10: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

10

 ANN’s: an Operational View

Discontinuous Output

Input S

ignals yk

Output

Signal

wk3

wk1

wk2

wk4

Neuron xk

x1

x2

x3

x4

bk

Summing Junction

Activation Function

)(1

)(0

****

:

1

1

44332211

THRESHOLDnetify

THRESHOLDnetify

outputSaturated

outputNeuronal

xwxwxwxwnet

sumweightedorinputNet

f(

net)

net

No output

Output

Threshold (θ)

(Normalised) output (eg. 1)

Page 11: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

11

 ANN’s: an Operational View

Input S

ignals yk

Output

Signal

wk3

wk1

wk2

wk4

Neuron xk

x1

x2

x3

x4

bk

Summing Junction

Activation Function

The notion of a discontinuous function simulates the fundamental notion that biological neurons usually fire if there is ‘enough’ stimulus available in the environment.

But discontinuous is biologically implausible, so there must be some degree of continuity in the output such that an artificial neuron has a degree of biological plausibility.

Page 12: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

12

 ANN’s: an Operational View

Pseudo-Continuous Output

Input S

ignals yk

Output

Signal

wk3

wk1

wk2

wk4

Neuron xk

x1

x2

x3

x4

bk

Summing Junction

Activation Function

),,,(

)(

)(

****

:

'1

'1

1

44332211

fy

THRESHOLDSaturationnetify

THRESHOLDnetify

outputSaturated

outputNeuronal

xwxwxwxwnet

sumweightedorinputNet

f(

net)

net

Output=α

Output βThreshold (θ)

Saturation Threshold (θ’)

Page 13: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

13

 ANN’s: an Operational

View

A schematic for an 'electronic' neuron

ykwk3

wk1

wk2

wk4

Neuron xkx1

x2

x3

x4bk

Input Signals

Output

Signal

Summing Junction

Activation Function

Page 14: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

14

ANN’s: an Operational View

Neural Nets as directed graphsA directed graph is a geometrical object consisting of a set of points (called nodes) along with a set of directed line segments (called links) between them. A neural network is a parallel distributed information processing structure in the form of a directed graph.

Page 15: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

15

 ANN’s: an Operational

View

Input Connections

Processing Unit

Output Connection

Fan Out

Page 16: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

16

 ANN’s: an Operational

View

A neural network comprisesA set of processing unitsA state of activationAn output function for each unitA pattern of connectivity among unitsA propagation rule for propagating patterns of activities through the network An activation rule for combining the inputs impinging on a unit with the current state of that unit to produce a new level of activation for the unitA learning rule whereby patterns of connectivity are modified by experienceAn environment within which the system must operate

Page 17: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

17

 The McCulloch-Pitts Network

. McCulloch and Pitts demonstrated that any logical function can be duplicated by some network of all-or-none neurons referred to as an artificial neural network (ANN).

Thus, an artificial neuron can be embedded into a network in such a manner as to fire selectively in response to any given spatial temporal array of firings of other neurons in the ANN.

Artificial Neural Networks for Real Neuroscientists: Khurshid Ahmad, Trinity College, 28 Nov 2006

Page 18: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

18

 The McCulloch-Pitts

Network

Demonstrates that any logical function can be implemented by some network of neurons.

•There are rules governing the excitatory and inhibitory pathways.•All computations are carried out in discrete time intervals.•Each neuron obeys a simple form of a linear threshold law: Neuron fires whenever at least a given (threshold) number of excitatory pathways, and no inhibitory pathways, impinging on it are active from the previous time period.•If a neuron receives a single inhibitory signal from an active neuron, it does not fire.•The connections do not change as a function of experience. Thus the network deals with performance but not learning.

Page 19: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

19

 The McCulloch-Pitts

Network

Computations in a McCulloch-Pitts Network

‘Each cell is a finite-state machine and accordingly operates in discrete time instants, which are assumed synchronous among all cells. At each moment, a cell is either firing or quiet, the two possible states of the cell’ – firing state produces a pulse and quiet state has no pulse. (Bose and Liang 1996:21)

‘Each neural network built from McCulloch-Pitts cells is a finite-state machine is equivalent to and can be simulated by some neural network.’ (ibid 1996:23)

‘The importance of the McCulloch-Pitts model is its applicability in the construction of sequential machines to perform logical operations of any degree of complexity. The model focused on logical and macroscopic cognitive operations, not detailed physiological modelling of the electrical activity of the nervous system. In fact, this deterministic model with its discretization of time and summation rules does not reveal the manner in which biological neurons integrate their inputs.’ (ibid 1996:25)

Page 20: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

20

 The McCulloch-Pitts

Network

Consider a McCulloch-Pitts network which can act as a minimal model of the sensation of heat from holding a cold object to the skin and then removing it or leaving it on permanently.

Each cell has a threshold of TWO, hence fires whenever it receives two excitatory (+) and no inhibitory (-) signals from other cells at a previous time.

Artificial Neural Networks for Real Neuroscientists: Khurshid Ahmad, Trinity College, 28 Nov 2006

Page 21: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

21

 The McCulloch-Pitts

Network

1

3

A

B

42

-

+

+

+ +

++

+ +

+

+

Heat

Receptors Cold

Hot

Cold

Heat Sensing Network

Page 22: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

22

 The McCulloch-Pitts

Network

1

3

A

B

42

-

+

+

+ +

++

+ +

+

+

Heat

Receptors Cold

Hot

Cold

Heat Sensing Network

Time Cell 1 Cell 2 Cell a Cell b Cell 3 Cell 4

INPUT INPUT HIDDEN HIDDEN OUTPUT OUTPUT

1 No Yes No No No No

2 No No Yes No No No

3 No No No Yes No No

4 No No No No Yes No

Truth tables of the firing neurons when the cold object contacts the skin and is then removed

Page 23: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

23

 The McCulloch-Pitts

Network

Heat Sensing Network

‘Feel hot’/’Feel cold’ neurons show how to create OUTPUT UNIT RESPONSE to given INPUTS that depend ONLY on the previous values. This is known as a TEMPORAL CONTRAST ENHANCEMENT.

The absence or presence of a stimulus in the PREVIOUS time cycle plays a major role here.

The McCulloch-Pitts Network demonstrates how this ENHANCEMENT can be simulated using an ALL-OR-NONE Network.

Page 24: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

24

 The McCulloch-Pitts

NetworkHeat Sensing Network

Time Cell 1 Cell 2 Cell a Cell b Cell 3 Cell 4

INPUT INPUT HIDDEN HIDDEN OUTPUT OUTPUT

1

2

3

Truth tables of the firing neurons for the case when the cold object is left in contact with the skin – a simulation of temporal contrast enhancement

Page 25: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

25

 The McCulloch-Pitts

NetworkHeat Sensing Network

Time Cell 1 Cell 2 Cell a Cell b Cell 3 Cell 4

INPUT INPUT HIDDEN

HIDDEN

OUTPUT

OUTPUT

1 No Yes No No No No

2 No Yes Yes No No No

3 No Yes Yes No No Yes

Truth tables of the firing neurons for the case when the cold object is left in contact with the skin – a simulation of temporal contrast enhancement

1

3

A

B

42

-

+

+

+ +

++

+ +

+

+

Heat

Receptors Cold

Hot

Cold

Page 26: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

26

 The McCulloch-Pitts

Network

+

++

+

+ + +

+

1 2

A

B

1 2+

+

Memory Models

Three stimulus model

Permanent Memory model

+

+

Page 27: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

27

 The McCulloch-Pitts

Network

In the permanent memory model, the output neuron has threshold ‘1’; neuron 2 fires if the light has ever been on anytime in the past.Levine, D. S. (1991:16)

1 2+

+

Memory Models

Permanent Memory model

Page 28: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

28

 The McCulloch-Pitts

NetworkMemory Models

1 2

A

B

Three stimulus model

Time Cell 1 Cell A Cell B Cell 2

1 Yes No No No

2 Yes No Yes No

3 Yes Yes Yes No

4 No Yes Yes Yes

Consider, the three stimulus all-or-none neural network. In this network, neuron 1 responds to a light being on. Each of the neurons has threshold ‘3’.

In the three stimulus model neuron 2 fires after the light has been on three time units in a row.

All connections are unit positive

Page 29: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

29

 The McCulloch-Pitts

Network

Why is a McCulloch-Pitts a FSM?

A finite state machine (FSM)is an AUTOMATON.An input string is read from left to right; the machine looks at each symbol in turn. At any time the FSM is in one of many finitely interval states.The state changes after each input symbol is read.The NEW STATE depends (only) on the symbol just read and on the current state.

Page 30: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

30

 The McCulloch-Pitts Network

Artificial Neural Networks for Real Neuroscientists: Khurshid Ahmad, Trinity College, 28 Nov 2006

‘The McCulloch-Pitts model, though it uses an oversimplified formulation of neural activity patterns, presages some issues that are still important in current cognitive models. [..][Some] Modern connectionist networks contain three types of units or nodes – input units, output units, and hidden units. The input units react to particular data features from the environment […]. The output units generate particular organismic responses […]. The hidden units are neither input nor output units themselves but, via network connections, influence output units to respond to prescribed patterns of input unit firings or activities. [..] [This] input-output-hidden trilogy can be seen as analogous to the distinction between sensory neurons, motor neurons, and all other (interneurons) in the brain’

Levine, Daniel S. (1991: 14-15)

Page 31: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

31

 The McCulloch-Pitts Network

Linear Neuron: Output is the weighted sum of all the inputs;McCulloch-Pitts Neuron: Output is the thresholded value of the weighted sumInput Vector? X = X (1,-20,4,-2); Weight vector? wji=w(wj1,wj2,wj3,wj4)

=[0.8,0.2,-1,-0.9]

0th input

x1

x2

x3

x4

yjj

wj1

wj2

wj3

wj4

Page 32: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

32

 The McCulloch-Pitts Network

vj=wjixi; y=f(v); y=0 if v<=0 or y=1 if v>0Input Vector? X = X (1,-20,4,-2); Weight vector? wji=w(wj1,wj2,wj3,wj4)

=[0.8,0.2,-1,-0.9]wj0=0, x0=0

0th input

x1

x2

x3

x4

yjj

wj1

wj2

wj3

wj4

Page 33: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

33

 The McCulloch-Pitts Network

Input Vector? X = X (1,-20,4,-2); Weight vector? w=w(wj1,wj2,wj3,wj4)

=[0.8,0.2,-1,-0.9]wj0=0, x0=0

vj=wjixi; y=f(v); f activation functionLinear Neuron: y=vMcCulloch Pitts: y=0 if v<=0 or y=1 if v>0Sigmoid activation function: f(v)=1 /(1+exp(-v))

Page 34: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

34

 The McCulloch-Pitts Network

What are the circumstance in a neuron with a sigmoidal activation function will act like a McCulloch Pitts network?

Large synaptic weights

What are the circumstance in a neuron with a sigmoidal activation function will act like a linear neuron?

Small synaptic weights

Page 35: 1 Financial Informatics –XIV: Basic Principles 1 Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2,

35

 The McCulloch-Pitts Network

The key outcome of early research in artificial neural networks clearly demonstrated the theoretical importance (brain like behaviour and logical basis) and extensive utility (regime switching modes) of threshold behaviour. This behaviour was emulated through the use of the squashing functions and is the basis of many a simulation.