The document provides an overview of artificial neural networks. It begins by defining neural networks and comparing the brain to a computer. It then discusses the biological brain in more detail, including neurons, synapses, and how connections change with experience. The document outlines the evolution of neural networks and their key characteristics. It also models different aspects of neural networks including their structure, weighted connections, and learning algorithms like backpropagation. Finally, it provides examples of neural network applications such as pattern recognition, forecasting, and use in manufacturing decision support systems.

1. SUBMITTED TO: SUBMITTED BY:
DR. Y. M. PURI MOHSIN DALVI
ASSOCIATE PROFESSOR 13MT07IND014
COURSE COORDINATOR FOR M. TECH (INDL. ENGG)
AUTOMATION IN PRODUCTION SEM-II, SUMMER 2014
PRESENTATION ON
ARTIFICIAL NEURAL NETWORKS
VISVESVARAYA NATIONAL INSTITUTE OF TECHNOLOGY, NAGPUR 440010
DEPARTMENT OF MECHANICAL ENGINEERING

2. Introduction
Artificial
Neural
Networks
2

3. What are Neural Networks?
 An artificial neural network is a biologically inspired
computational model that consists of processing elements
(neurons) and connections between them, as well as of training
and recall algorithms.
 The network is usually implemented using electronic components
or simulated in software on a digital computer.
 Neural Networks attempt to bring computers a little closer to the
brain's capabilities by imitating certain aspects of information
processing in the brain, in a highly simplified way.
Introduction
3

4. The Brain vs A ComputerIntroduction
Brain Computer
Processing Elements 1010 neurons 108 transistors
Element Size 10-6 m 10-6 m
Energy Use 30 W 30 W (CPU)
Processing Speed 102 Hz 1012 Hz
Style Of Computation Parallel, Distributed Serial, Centralized
Energetic Efficiency 10-16 joules/opn/sec 10-6 joules/opn/sec
Fault Tolerant Yes No
Learns Yes A little
4

5. Characteristics of a Biological Brain
 Massively parallel, distributed information processing
 High degree of connectivity among basic units
 Connections get reorganized based on experience
 Performance degrades gracefully if some units are removed (i.e.
some nerve cells die)
 Learning is constant and usually unsupervised
 Learning is based only on local information
Introduction
5

6. The Biological Brain
 Neurons: Fundamental information-processing units of the brain.
 Neurons contain axons (the transmission lines) and dendrites,
(the receptive zones).
 Electrical signal flows from dendrites to axon.
Introduction
6

7. The Biological Brain
 Synapses are elementary structural and functional units that
mediate the interactions between neurons.
 Synapse converts a presynaptic electrical signal into a chemical
signal and then back into a postsynaptic electrical signal.
 During the early stage of development
(first two years from birth), about 1 million
synapses are formed per second.
 In an adult’s brain, a neuron is connected to
around 10,000 other neurons by synapses.
Introduction
7

8. Evolution of Neural Networks
 1911 - Ramon y Cajal introduced the idea of neurons as structural
constituents of the brain
 1943 - McCulloch and Pitts apply Boolean algebra to nerve
net behaviour
 1948 - Donald Hebb postulates qualitative mechanism for
learning at cellular level in brains
 1957 - Rosenblatt develops ‘perceptron’ neurocomputer
 Between 1960’s & 1980’s - Almost no research in ANN
 Middle 80's - John Hopfield revives ANN
 Today - ANN one of the most active current areas of research
Introduction
9

9. Characteristics of Neural NetworksIntroduction
 Universal Regression Systems - Modeling of a system with an
unknown input-output relationship
 Learning - Network with "no knowledge“ can be trained with set
of paired input-output data to give desired outputs for known
inputs.
 Generalization - Produce best output according to learned
examples if a different vector is input into network.
 Adaptivity - Adapt response to changes in surrounding
environment
10

10. Characteristics of Neural NetworksIntroduction
 Nonlinearity - Cope with nonlinear data and environment
 Massive parallel processing - Many neurons fire simultaneously
during data processing
 Fault Tolerance - Good response even if input data is slightly
incorrect
 Robustness - Whole system can still perform well even if some
neurons "go wrong"
11

11. Neural Networks Modeling
Artificial
Neural
Networks
12

12. Input
Output
Node
Node
Node
Node
Node
Node
Node
Node Node
Representation of Neural Networks
Neural
Networks
Modeling
Connections
13

13. OUTPUTS
B
A
INPUTS
2
1
3
/ * + -
AND OR
IF GOTO
Conventional Computer Model
Neural
Networks
Modeling
14

14. HIDDEN LAYER
OUTPUT
LAYER
INPUT LAYER
Neural Network As A Computer Model
Neural
Networks
Modeling
Connections
Nodes
15

15. HIDDEN LAYER
OUTPUT
LAYER
INPUT LAYER
Directed
Connections
Neural Network As A Computer Model
Neural
Networks
Modeling
16

16. HIDDEN LAYER
OUTPUT
LAYER
INPUT LAYER
Weighted
Connections
Neural Network As A Computer Model
Neural
Networks
Modeling
17

17. HIDDEN LAYER
INPUT LAYER
A
B
C
Effect of Weighted Connections
Neural
Networks
Modeling
18
+ =A B C
EQUAL PROPORTIONS:
R - 0
G - 255
B - 0
R - 255
G - 0
B - 0
R - 255
G - 255
B - 0
+ =A B C
WEIGHTED PROPORTIONS:
R - 0
G - 127
B - 0
R - 255
G - 0
B - 0
R - 255
G - 127
B - 0

18. OUTPUT
LAYER
HIDDEN LAYER
Example of Weighted Connections
Neural
Networks
Modeling
INPUT LAYER
19

19. Decision Making in Neural Networks
Neural
Networks
Modeling
HIDDEN LAYERINPUT LAYER OUTPUT
LAYER
DESIRED
OUTPUTS
ACCURACY DECISION:
HOW TO UPDATE WEIGHTS TO REDUCE ERROR?
ERROR
20

20. Thresholding in Biological Neural NetworkIntroduction
21

21. Reflex Action in Biological Neural NetworkIntroduction
22

22. INPUT LAYER
A
B
C
Decision Making in Neural Networks
Neural
Networks
Modeling
ACTIVATION DECISION:
WHEN SHOULD THE NODE FIRE ITS OUTPUT?
23

23. Neural Networks Modeling Aspects
 Fundamental issues in modeling of an artificial neural network:
• How to assign weights to the connections?
• How to determine the neuron output threshold?
 Major steps in modeling an artificial neural network:
• Model a single neuron
• Establish a pattern of neuron interconnectivity
• Implement a learning mechanism
Neural
Networks
Modeling
24

24. Modeling an Artificial Neuron
Neural
Networks
Modeling
25
 Perceptron Model: Developed by Rosenblatt in 1957.
 Other neuron models are adaptations of perceptron model
μk=Σwkjxj
νk=μk-bk
νk
yk=φ(νk) yk
θk
Threshold
Output
Activation
Function
Integration
Function
---
x2 wk2
x1 wk1
xn wkn
---

25. Perceptron Model of Neuron
 Input signals:
• Continuous or discrete values fed from previous neurons
• Each input associated with a Weight
 Integration Function:
• Usually a weighted summation function
• Threshold/Bias regulates result of Integration Function
• Output is called neuron net input
 Activation/Transfer Function:
• Usually a non linear function
• Output interval [0,1] or [-1,1]
• Output values continuous or discrete
Neural
Networks
Modeling
26
-1
-0.5
0
0.5
1
1.5
-2 -1 0 1 2
Sigmoid Heaviside Linear

26. Perceptron Model Example
Neural
Networks
Modeling
27
Summing Function:
μ = w1x1 + w2x2 + w3x3
= 3(0.2) + 1(0.4) + 2(0.1)
= 1.2
Activation Function:
77.0
1
1
1
1
2.1




 
ee
y 
w2 = 0.4
x2 = 1
x3 = 2
x1 = 3
y

27. Connecting Neurons to Build Networks
Neural
Networks
Modeling
28Recurrent Network Lattice Network
Single Layer Feedforward Network
Input
Layer
Output
Layer
Multi- Layer Feedforward Network
Input
Layer
Output
Layer
Hidden
Layer 1
Hidden
Layer 2

28. Supervised Learning Unsupervised Learning
Binary Valued
Input
• Hopfield Network
• Boltzmann Machine
• ART I
Continuous Valued
Input
• Backpropagation
• Percepteron
• ART II
• Self-Organising
Feature Maps
Learning Algorithms in Neural Networks
Neural
Networks
Modeling
29

29. Compute Output
Adjust Weights
Stop
Is Desired
Output
Achieved?
Yes
No
Supervised Learning in Neural Networks
Neural
Networks
Modeling
30

30. First Run of the Network
Neural
Networks
Modeling
HIDDEN LAYER
OUTPUT
LAYER
INPUT LAYER
14
29
41
DESIRED
OUTPUTS
35
45
17
ERROR
21
16
-24
31

31. ERROR
21
16
-24
Backpropagation of Output Error
Neural
Networks
Modeling
HIDDEN LAYER
INPUT LAYER
-11
19
3
19
-5
32
0
14
26
-12
-8
32

32. OUTPUT
LAYER
HIDDEN LAYER
Second Run of the Network
Neural
Networks
Modeling
INPUT LAYER
20
32
29
DESIRED
OUTPUTS
35
45
17
ERROR
15
13
-12
33

33. ERROR
(RUN 1)
21
16
-24
Reduction of Output Error
Neural
Networks
Modeling
ERROR
(RUN 2)
15
13
-12
ERROR
(RUN N)
0
0.01
0
- - - -
34

34. After Many Runs of the Network
Neural
Networks
Modeling
HIDDEN LAYER
INPUT LAYER
OUTPUT
LAYER
35
45
17
35

35. Collect Data
Separate into Training and Test Sets
Define Network Structure
Select Learning Algorithm
Select Parameters, Values, Initialise Weights
Transform Data into Network Inputs
Start Training and Determine and Revise Weights
Stop and Test
Implementation: Use the Network with New Cases
Get More, Better Data
Reseparate
Redefine Structure
Select Another Algorithm
Reset
Reset
Developing a Neural Network
Neural
Networks
Modeling
36

36. Neural Networks Applications
Artificial
Neural
Networks
37

37. What are neural networks used for?
Neural
Networks
Applications
 Classification: Assigning each object to a known specific class
 Clustering: Grouping together objects similar to each other
 Pattern Association: Presenting of an input sample triggers the
generation of specific output pattern
 Function approximation: Constructing a function generating
almost the same outputs from input data as the modeled process
 Optimization: Optimizing function values subject to constraints
 Forecasting: Predicting future events on the basis of past history
 Control: Determining values for input variables to achieve desired
values for output variables
38

38. Unknown
Character
Feature
Recognition
Neurons
0 1 2 3 4 5 6 7 8 9 Classifier
Neurons
Recognised Character
ANN Feature Recognition (OCR Software)
Applications
of Neural
Networks
39

39. Neural Networks in Manufacturing
Neural
Networks
Applications
 Manufacturing process decision problem:
 Neural network enabled decision support system:
Manufacturing
System
State Variables
Process Settings
Process OutcomesProcess Variables
Trained Neural
Network
Training Algorithm
Production Data
Step 1: Train the
Network
Optimization
Procedure
Recommended
Process Setting
Current Values of
State and Process
Variables
Step 2: Use the network to aid in
decision making process
40
Trained Neural
Network

40. Neural Networks in Manufacturing
Neural
Networks
Applications
 Modeling and Design of Manufacturing Systems
• Cell Formation for Agile and Flexible Manufacturing
• Optimization and Simulation of manufacturing system
• Forecasting and Cost Estimation
• AGV path determination
 Modeling, Planning, and Scheduling of Manufacturing Processes
• Production and Machine-scheduling
• Kanban Determination
• Resource queuing and scheduling
• Economic order quantity
41

41. Neural Networks in Manufacturing
Neural
Networks
Applications
 Monitoring and Control of Manufacturing Processes
• Parameter Selection
• Automated Process Control eg: pressing, rolling, welding, EDM, WEDM
• Condition Monitoring for Machines and Tools
• Robot part handling
 Quality Control, Quality Assurance, and Fault Diagnosis
• Recognizing Handwritten Characters and Graphs
• Visual Edge Detection
• Pattern recognition
• Fault Diagnosis and Troubleshooting
42

42. Neural Networks in Injection Moulding
Neural
Networks
Applications
43

43. Neural Networks in Injection Moulding
Neural
Networks
Applications
44

44. Neural Networks in Injection Moulding
Neural
Networks
Applications
 Neural Network Configuration: 27-10-1
 Correlation coefficient = 0.9254
 RMSE = 1.3%-19%
45

45. Final Words
Applications
of Neural
Networks
“ Artificial neural networks are still far away from biological
neural networks , but what we know today about artificial
neural networks is sufficient to solve many problems that
were previously unsolvable or inefficiently solvable at best. ”
46

46. End Of Presentation
Artificial
Neural
Networks
47