In this presentation, I explain the introduction of Artificial Neural Network in medical diagnosis.

1. Institute of Engineering and Technology Lucknow
A Seminar Presentation
On
Artificial Neural Networks
Represented By:
Adityendra Kumar Singh
Enroll No: 170521403400
Department of Computer Science and Engineering

2. Table of Contents
• What Is An Artificial Neural Network?
• Structure Of A Biological Neural Network
• Comparison Of Biological Neuron And Artificial
Neuron
• Structure Of ANN
• Artificial Neural Network Concepts
• Types of Artificial Neural Network
• Perceptron and Multilayer Perceptron—the
Foundation of Neural Networks

3. • Understanding Back propagation in Neural
Networks
• Understanding Neural Network Activation
Functions
• Definition of Bias vs. Variance in Neural Networks
• Over fitting and Under fitting in Neural Networks
• Artificial Neural Network Applications
• Limitations Of Neural Networks
• Conclusion
• References

4. What Is An Artificial Neural Network?
• Artificial Neural Network is analogous to a biological neural
network. A biological neural network is a structure of
billions of interconnected neurons in a human brain. The
human brain comprises of neurons that send information
to various parts of the body in response to an action
performed.
• ANN consist of a large number of interconnected neurons
that are inspired by the working of a brain. These neurons
have the capabilities to learn, generalize the training data
and derive results from complicated data.
• The formal definition of ANN given by Dr. Robert Hecht-
Nielson, inventor of one first neuro computers is:
“…a computing system made up of a number of simple,
highly interconnected processing elements, which process
information by their dynamic state response to external
inputs”.

5. Structure Of A Biological Neural Network
A biological neural network
consists of:
• Soma: Process the inputs.
• Dendrites: Accepts the
inputs
• Axon: Turns the processed
inputs into outputs.
• SYNAPSES : The
electrochemical contact
between the neurons.

6. Comparison Of Biological Neuron And
Artificial Neuron

7. Structure Of ANN
Artificial Neural Networks (ANN) is a supervised learning
system built of a large number of simple elements, called
neurons or perceptrons. Each neuron can make simple
decisions, and feeds those decisions to other neurons,
organized in interconnected layers. Together, the neural
network can emulate almost any function, and answer
practically any question, given enough training samples and
computing power. A “shallow” neural network has only
three layers of neurons:
• An input layer that accepts the independent variables or
inputs of the model
• One hidden layer
• An output layer that generates predictions
• A Deep Neural Network (DNN) has a similar structure, but it
has two or more “hidden layers” of neurons that process
inputs.

8. Artificial Neural Network Concepts
Here is a glossary of basic terms you should be
familiar with before learning the details of neural
networks.
• Inputs: Source data fed into the neural network,
with the goal of making a decision or prediction
about the data. Inputs to a neural network are
typically a set of real values; each value is fed into
one of the neurons in the input layer.
• Training Set: A set of inputs for which the correct
outputs are known, used to train the neural
network.

9. • Outputs : Neural networks generate their
predictions in the form of a set of real values
or Boolean decisions. Each output value is
generated by one of the neurons in the output
layer.
• Neuron/perceptron : The basic unit of the
neural network. Accepts an input and
generates a prediction.

10. • Weight Space : Each neuron is given a numeric
weight. The weights, together with the activation
function, define each neuron’s output. Neural
networks are trained by fine-tuning weights, to
discover the optimal set of weights that
generates the most accurate prediction.
• Forward Pass: The forward pass takes the inputs,
passes them through the network and allows
each neuron to react to a fraction of the input.
Neurons generate their outputs and pass them
on to the next layer, until eventually the network
generates an output.

11. • Error Function: Defines how far the actual output of
the current model is from the correct output. When
training the model, the objective is to minimize the
error function and bring output as close as possible to
the correct value.
• Back propagation : In order to discover the optimal
weights for the neurons, we perform a backward pass,
moving back from the network’s prediction to the
neurons that generated that prediction. This is called
back propagation. Back propagation tracks the
derivatives of the activation functions in each
successive neuron, to find weights that brings the loss
function to a minimum, which will generate the best
prediction. This is a mathematical process
called gradient descent.

12. • Bias and Variance : When training neural networks,
like in other machine learning techniques, we try to
balance between bias and variance. Bias measures
how well the model fits the training set—able to
correctly predict the known outputs of the training
examples. Variance measures how well the model
works with unknown inputs that were not available
during training. Another meaning of bias is a “bias-
neuron” which is used in every layer of the neural
network. The bias neuron holds the number 1, and
makes it possible to move the activation function up,
down, left and right on the number graph.

13. • Hyper parameters : A hyper parameter is a
setting that affects the structure or operation
of the neural network. In real deep learning
projects, tuning hyper parameters is the
primary way to build a network that provides
accurate predictions for a certain problem.
Common hyper parameters include the
number of hidden layers, the activation
function, and how many times (epochs)
training should be repeated.

14. Types of Artificial Neural Networks
There are several kinds of artificial neural networks. These
types of networks are implemented based on the
mathematical operations and a set of parameters required to
determine the output.
1. Feedforward Neural Network
2. Radial basis function Neural Network
3. Kohonen Self Organizing Neural Network
4. Recurrent Neural Network(RNN) – Long Short Term
Memory
5. Convolutional Neural Network
6. Modular Neural Network

15. 1. Feedforward Neural Network
This neural network is one of the simplest forms
of ANN, where the data or the input travels in
one direction. The data passes through the input
nodes and exit on the output nodes. This neural
network may or may not have the hidden layers.

16. 2. Radial basis function Neural Network
Radial basic functions consider the distance of a point
with respect to the center. RBF functions have two
layers, first where the features are combined with the
Radial Basis Function in the inner layer and then the
output of these features are taken into consideration
while computing the same output in the next time-step
which is basically a memory.

17. 3. Kohonen Self Organizing Neural Network
The objective of a Kohonen map is to input
vectors of arbitrary dimension to discrete map
comprised of neurons. The map needs to be
trained to create its own organization of the
training data. It comprises either one or two
dimensions. When training the map the location
of the neuron remains constant but the weights
differ depending on the value. This self-
organization process has different parts, in the
first phase, every neuron value is initialized with a
small weight and the input vector.
Cont…

19. 4. Recurrent Neural Network(RNN) – Long Short
Term Memory
The Recurrent Neural Network works on the
principle of saving the output of a layer and
feeding this back to the input to help in
predicting the outcome of the layer.

20. 5. Convolutional Neural Network
Convolutional neural networks are similar to
feed forward neural networks, where the
neurons have learnable weights and biases. Its
application has been in signal and image
processing which takes over OpenCV in the
field of computer vision.

21. 6. Modular Neural Network
Modular Neural Networks have a collection of different
networks working independently and contributing
towards the output. Each neural network has a set of
inputs that are unique compared to other networks
constructing and performing sub-tasks. These networks
do not interact or signal each other in accomplishing
the tasks.

22. Perceptron and Multilayer Perceptron—the Foundation of
Neural Networks
• What is a Perceptron?
A perceptron is a binary
classification algorithm
modeled after the
functioning of the
human brain—it was
intended to emulate the
neuron. The perceptron,
while it has a simple
structure, has the ability
to learn and solve very
complex problems.

23. What is Multilayer Perceptron?
A multilayer perceptron
(MLP) is a group of
perceptrons, organized
in multiple layers, that
can accurately answer
complex questions.
Each perceptron in the
first layer (on the left)
sends signals to all the
perceptrons in the
second layer, and so
on. An MLP contains an
input layer, at least one
hidden layer, and an
output layer.

24. The Perceptron Learning Process
The perceptron learns as follows:
• Takes the inputs which are fed into the perceptrons in
the input layer, multiplies them by their weights, and
computes the sum.
• Adds the number one, multiplied by a “bias weight”.
This is a technical step that makes it possible to move
the output function of each perceptron (the activation
function) up, down, left and right on the number
graph.
• Feeds the sum through the activation function—in a
simple perceptron system, the activation function is a
step function.
• The result of the step function is the output.

26. From Perceptron to Deep Neural
Network
A multilayer perceptron is quite similar to a modern
neural network. By adding a few ingredients, the
perceptron architecture becomes a full-fledged deep
learning system:
Activation functions and other hyper parameters —a
full neural network uses a variety of activation
functions which output real values, not boolean values
like in the classic perceptron. It is more flexible in
terms of other details of the learning process, such as
the number of training iterations (iterations and
epochs), weight initialization schemes, regularization,
and so on. All these can be tuned as hyper parameters.

27. • Back propagation—a full neural network uses the
back propagation algorithm, to perform iterative
backward passes which try to find the optimal
values of perceptron weights, to generate the
most accurate prediction.
• Advanced architectures—full neural networks
can have a variety of architectures that can help
solve specific problems. A few examples are
Recurrent Neural Networks (RNN), Convolutional
Neural Networks (CNN), and Generative
Adversarial Networks (GAN).

28. Understanding Back propagation in
Neural Networks
• What is Back propagation and Why is it Important?
After a neural network is defined with initial weights,
and a forward pass is performed to generate the initial
prediction, there is an error function which defines how
far away the model is from the true prediction. There are
many possible algorithms that can minimize the error
function—for example, one could do a brute force search
to find the weights that generate the smallest error.
However, for large neural networks, a training algorithm
is needed that is very computationally efficient. Back
propagation is that algorithm—it can discover the
optimal weights relatively quickly, even for a network
with millions of weights.

29. How Back propagation Works
• Forward pass—weights are initialized and inputs from the
training set are fed into the network. The forward pass is
carried out and the model generates its initial prediction.
• Error function—the error function is computed by checking
how far away the prediction is from the known true value.
• Back propagation with gradient descent—the back
propagation algorithm calculates how much the output
values are affected by each of the weights in the model. To
do this, it calculates partial derivatives, going back from the
error function to a specific neuron and its weight. This
provides complete traceability from total errors, back to a
specific weight which contributed to that error. The result
of back propagation is a set of weights that minimize the
error function.

30. • Weight update—weights can be updated after
every sample in the training set, but this is
usually not practical. Typically, a batch of
samples is run in one big forward pass, and
then back propagation performed on the
aggregate result. The batch size and number
of batches used in training, called iterations,
are important hyper parameters that are
tuned to get the best results. Running the
entire training set through the back
propagation process is called an epoch.

31. Understanding Neural Network
Activation Functions
• Activation functions are central to deep learning
architectures. They determine the output of the model, its
computational efficiency, and its ability to train and
converge after multiple iterations of training.
• What is a Neural Network Activation Function?
An activation function is a mathematical equation that
determines the output of each element (perceptron or
neuron) in the neural network. It takes in the input from
each neuron and transforms it into an output, usually
between one and zero or between -1 and one. Classic
activation functions used in neural networks include the
step function (which has a binary input), sigmoid and tanh.
New activation functions, intended to improve
computational efficiency, include ReLu and Swish.

32. Role of the Activation Function
• In a neural network, inputs, which are typically real
values, are fed into the neurons in the network. Each
neuron has a weight, and the inputs are multiplied by
the weight and fed into the activation function.
• Each neuron’s output is the input of the neurons in the
next layer of the network, and so the inputs cascade
through multiple activation functions until eventually,
the output layer generates a prediction. Neural
networks rely on nonlinear activation functions—the
derivative of the activation function helps the network
learn through the back propagation process.

34. 7 Common Activation Functions
• The sigmoid function has a smooth gradient and outputs
values between zero and one. For very high or low values of
the input parameters, the network can be very slow to
reach a prediction, called the vanishing gradient problem.
• The Tanh function is zero-centered making it easier to
model inputs that are strongly negative strongly positive or
neutral.
• The ReLu function is highly computationally efficient but is
not able to process inputs that approach zero or negative.
• The Leaky ReLu function has a small positive slope in its
negative area, enabling it to process zero or negative
values.

35. • The Parametric ReLu function allows the negative
slope to be learned, performing back propagation
to learn the most effective slope for zero and
negative input values.
• Softmax is a special activation function use for
output neurons. It normalizes outputs for each
class between 0 and 1, and returns the
probability that the input belongs to a specific
class.
• Swish is a new activation function discovered by
Google researchers. It performs better than ReLu
with a similar level of computational efficiency.

36. Definition of Bias vs. Variance in
Neural Networks
To understand bias vs. variance, we first need to
introduce the concept of a training set and validation
set:
• A training set is a group of examples which is fed to the
neural network during training.
• A validation set is a group of unseen examples which
you use to test your neural network to see how it
performs.
• An error function calculates the error, for either the
training or validation sets. The error reflects how far
away the network’s actual predictions were compared
to the known correct outputs.

37. • Bias reflects how well the model fits the
training set. A high bias means the neural
network is not able to generate correct
predictions even for the examples it trained
on. Variance reflects how well the model fits
unseen examples in the validation set. A high
variance means the neural network is not able
to correctly predict for new examples it hasn’t
seen before.

39. Over fitting and Under fitting in
Neural Networks
Over fitting happens when the neural network
is good at learning its training set, but is not
able to generalize its predictions to additional,
unseen examples. This is characterized by low
bias and high variance. Under fitting happens
when the neural network is not able to
accurately predict for the training set, not to
mention for the validation set. This is
characterized by high bias and high variance.

40. Methods to Avoid Over fitting
Here are a few common methods to avoid over fitting in neural
networks:
• Retraining neural networks—running the same model on the same
training set but with different initial weights, and selecting the
network with the best performance.
• Multiple neural networks—training several neural network models
in parallel, with the same structure but different weights, and
averaging their outputs.
• Early stopping—training the network, monitoring the error on the
validation set after each iteration, and stopping training when the
network starts to overfit the data.
• Regularization—adding a term to the error function equation,
intended to decrease the weights and biases, smooth outputs and
make the network less likely to overfit.
• Tuning performance ratio—similar to regularization, but using a
parameter that defines by how much the network should be
regularized.

41. Methods to Avoid Underfitting
Here are a few common methods to avoid underfitting in a neural
network:
• Adding neuron layers or inputs—adding neuron layers, or
increasing the number of inputs and neurons in each layer, can
generate more complex predictions and improve the fit of the
model.
• Adding more training samples or improving quality—the more
training samples you feed into the network, and the better they
represent the variance in the real population, the better the
network will perform.
• Dropout—randomly “kill” a certain percentage of neurons in every
training iteration. This ensures some information learned is
randomly removed, reducing the risk of overfitting.
• Decreasing regularization parameter—regularization can be
overdone. By using a regularization performance parameter, you
can learn the optimal degree of regularization, which can help the
model better fit the data.

42. Applications Artificial Neural Network
Neural Networks have been successfully used in a variety of
solutions as shown below.
• Pattern Recognition: ANN is used in pattern recognition, image
recognition, visualization of images, handwriting, speech, and other
such tasks.
• Optimization Problems: Problems such as finding the shortest
route, scheduling and manufacturing where problem constraints
are to be satisfied and optimal solutions need to be achieved are
using NNs.
• Forecasting: NN can predict the outcome for situations by analyzing
past trends. Applications such as banking, stock market, weather
forecasting use Neural Networks.
• Control Systems: Control systems such as computer products,
chemical products, and robotics use neural networks.

43. Artificial Neural Networks in Medical
Diagnosis
Artificial neural networks (ANNs) are widely used in science
and technology with applications in various branches of
chemistry, physics, and biology. For example, ANNs are used in
chemical kinetics, prediction of the behavior of industrial
reactors , modeling kinetics of drug release. Here the overview
of the main applications of artificial neural networks in
medicine.
Cont…

44. ARTIFICIAL NEURAL NETWORKS
An ANN is a mathematical representation of the
human neural architecture, reflecting it learning
and generalization abilities.
Mathematical background
The neurons in the input layer receive the data and
transfer them to neurons in the first hidden layer
through the weighted links. The j-th neuron in a
hidden layer processes the incoming data (xi) by: (i)
calculating the weighted sum and adding a “bias”
term (θj) according to Eq. 1:
Cont…

45. General structure of a neural network with two hidden layers.
The wij is the weight of the connection between the i-th and
the j-th node.
Cont…

46. transforming the netj through a suitable mathematical
activation function and transferring the result to neurons in
the next layer.
Network learning
The network “learns” from a series of “examples” that form
the training database. An example is formed by a vector Xim =
(xi1, xi2, …., xim) of inputs and a vector Yin = (yi1, yi2,....., yin)
of outputs. The objective of the training process is to
approximate the function f between the vectors Xim and the
Yin:
Cont…

47. The values of the weights are changed by using
the steepest descent method to minimize a
suitable function used as the training stopping
criteria. One of the functions most commonly
used is the sum-of-squared residuals given by
Eq. 4:
where yij and yij* are the actual and network’s j-th
output corresponding to the i-th input vector,
respectively.
Cont…

48. The current weight change on a given layer is
given by Eq. (5):
where η is a positive constant called the learning
rate. To achieve faster learning and avoid local
minima, an additional term is used and Eq. 5
becomes:
Cont…

49. where μ is the “momentum” term and Δwij k-1 is the
change of the weight wij from the (k-1)-th learning
cycle. The learning rate controls the weight update
rate according to the new weight change and the
momentum acts as a stabilizer, being aware of the
previous weight change.
Details of input and output items concerning ANNs-based diagnosis (ANN architecture is
often hidden and it is indicated here as a black box).

50. Example of training database structure. Each row refers to a
different patient labeled with a numerical code. The element
data k,i refers to the i-th medical data (symptom, laboratory
data, etc.) of the k-th patient.
Cont…

51. Structure of the training database
The network must be trained using a suitable
database. The database is a table (or matrix) of
data concerning patients for whom the diagnosis
(positive or negative) about a certain disease is
already known. Each row of the matrix refers to
one patient. The first m elements of the row are
medical data and the last n elements represent
the output (diagnosis). The term “medical data”
indicates biochemical, nuclear magnetic resonance
(NMR), laboratory data, and symptoms and other
information provided by the medical specialist. An
example of such training matrix with one output
variable (n = 1) that may assume two possible
values (positive or negative).
Cont…

52. Example of the plot used to select the optimal number of
nodes in a given hidden layer. It is indicated that too high
number of nodes might lead to overfitting
Cont…

53. Cont…

54. OVERVIEW OF ANNs IN MEDICAL DIAGNOSIS
There are several reviews concerning the application of
ANNs in medical diagnosis.
Cardiovascular diseases
• Cardiovascular diseases (CVDs) are defined as all
diseases that affect the heart or blood vessels, both
arteries and veins.
• Based on a bibliography search (ScienceDirect), more
than one thousand papers about the use of ANNs in
cardiovascular diseases and related topics have been
published since 2008. According to the NCHS, coronary
artery disease (CAD) is currently the leading cause of
death worldwide, therefore early diagnosis is very
important.
Cont…

55. Cancer
• According to the American Cancer Society
(www.cancer.org), there will be more than 1.6 million
newly diagnosed cases of cancer in the US in 2012.
• The use of ANNs in distinguishing particular cancer
types or the prediction of cancer development
emerged in the late 1990s as a promising
computational-based diagnostic tool using various
inputs.
• The application of neural networks trained on defined
data sets was evaluated in 1994 for breast and ovarian
cancer, opening a discussion on the suitability of
particular data as inputs for ANN analysis.
Cont…

56. Diabetes
• Diabetes represents a serious health problem
in developed countries, with estimated
numbers reaching 366 million diabetes cases
globally in 2030.
• The standard in diabetes diagnosis or
monitoring is direct measurement of glucose
concentration in blood samples. The ANNs
extrapolate glucose concentrations from
spectral curve, thus enabling convenient
monitoring of diabetes during daily activities.

57. FUNDAMENTAL STEPS IN ANNs-BASED MEDICAL DIAGNOSIS
• The workflow of ANN analysis arising from the outlined
clinical situations is shown in below Fig. which provides a
brief overview of the fundamental steps that should be
followed to apply ANNs for the purposes of medical
diagnosis with sufficient confidence.
Diagram of fundamental steps in ANNs-based medical diagnosis. Building of the
database and “learning” represents the left half (green) and its application for the
diagnosis is the right part (blue).

58. • The network receives patient’s data to predict the
diagnosis of a certain disease. After the target disease
is established, the next step is to properly select the
features (e.g., symptoms, laboratory, and instrumental
data) that provide the information needed to
discriminate the different health conditions of the
patient.
• Therefore, careful selection of suitable features must
be carried out in the first stage. In the next step, the
database is built, validated and “cleaned” of outliers.
After training and verification, the network can be used
in practice to predict the diagnosis. Finally, the
predicted diagnosis is evaluated by a clinical specialist.
The major steps can be summarized as:
• Features selection
• Building the database
Data cleaning and preprocessing
Cont..

59. • Training and verification of database using ANN
Network type and architecture
Training algorithm
Verification
Robustness of ANN-based approaches
• Testing in medical practice
Features selection
Correct diagnosis of any disease is based on various, and
usually incoherent, data (features). The ability of ANNs to
learn from examples makes them very flexible and powerful
tools to accelerate medical diagnosis.
Cont...

60. Building the database
The neural network is trained using a suitable
database of “example” cases. An “example” is
provided by one patient whose values for the
selected features have been collected and
evaluated.
Training and verification of database using ANN
Although multilayer feed-forward neural
networks are most often used, there are a large
variety of other.networks including bayesian,
stochastic, recurrent, or fuzzy.
Training algorithm
Various training algorithms are available.
However, the most commonly used is back
propagation.
Cont…

61. Verification
ANNs-based medical diagnosis should be verified by
means of a dataset different from that one used for
training.
Robustness of ANN-based approaches
It is well known that ANNs are able to tolerate a certain
level of noise in the data and consequently they
typically provide sufficient prediction accuracy.
Testing in medical practice
As the final step in ANN-aided diagnosis should be
testing in medical practice. For each new patient the
network’s outcome is to be carefully examined by a
clinician. Medical data of patients for which the
predicted diagnosis is correct can be eventually
included in the training database.
Cont…

62. CONCLUSIONS
ANNs represent a powerful tool to help
physicians perform diagnosis and other
enforcements. In this regard, ANNs have
several advantages including:
(i) The ability to process large amount of data
(ii) Reduced likelihood of overlooking
relevant information
(iii) Reduction of diagnosis time.

63. ANN in Health Care Biometrics
• Biometrics is a powerful tool used in healthcare for
identification, insurance, and management.
• The benefits of biometric in healthcare is shown in
below Figure.
Cont…

64. Other potential benefits of identifying patients through
biometrics include:
• Preventing Medication Errors:
Biometrics can potentially replace patient wristbands
and barcodes as identifiers when nurses are
administering medication at the bedside.
• Reducing Billing Fraud:
Biometric identification can be used instead of paper
insurance cards, to prevent a common type of fraud
that occurs when one patient poses as another to
obtain insurance benefits. It can also deter
unscrupulous providers from filing phantom claims,
because a biometric scan offers proof of a patient’s
physical presence at a health care facility.
Cont…

65. • Improving the Capacity to React to Medical Emergencies:
With a fingerprint or palm scan, patients who are
unconscious or unable to talk can still be quickly identified
– along with pertinent medical history like drug allergies
and current medications.
• Furthering the State of Health Information Exchange (HIE):
When digitized patient information is shared regionally and
across providers, accurate patient identification is crucial.
When multiple records exist for the same patient, there’s a
strong likelihood that one or all will be incomplete.
potentially putting the patient at risk for drug interactions
or inappropriate services. Biometric patient identification
can eliminate the need for patients to fill out multiple
forms at each provider visit, and ensure that all data are
saved into the same patient record.

66. Business Applications of Neural Networks:
Here are several examples of ANN business
applications:
• Banking: Credit card attrition, credit and loan
application evaluation, fraud and risk evaluation, and
loan delinquencies.
• Business Analytics: Customer behavior modeling,
customer segmentation, fraud propensity, market
research, market mix, market structure, and models for
attrition, default, purchase, and renewals.
• Defense: Counterterrorism, facial recognition, feature
extraction, noise suppression, object discrimination,
sensors, sonar, radar and image signal processing,
signal/image identification, target tracking, and
weapon steering
Cont…

67. • Education: Adaptive learning software, dynamic
forecasting, education system analysis and forecasting,
student performance modeling, and personality
profiling
• Financial: Corporate bond ratings, corporate financial
analysis, credit line use analysis, currency price
prediction, loan advising, mortgage screening, real
estate appraisal, and portfolio trading
• Medical: Cancer cell analysis, ECG and EEG analysis,
emergency room test advisement, expense reduction
and quality improvement for hospital systems,
transplant process optimization, and prosthesis design
• Securities: Automatic bond rating, market analysis, and
stock trading advisory systems
• Transportation: Routing systems, truck brake diagnosis
systems, and vehicle scheduling

68. Other Application of ANN
Here are other aplications of ANN:
• Handwriting Recognition – The idea of Handwriting recognition has become
very important. This is because handheld devices like the Palm Pilot are
becoming very popular. Hence, we can use Neural networks to recognize
handwritten characters.
• Traveling Salesman Problem – Neural networks can also solve the traveling
salesman problem. But this is to a certain degree of approximation only.
• Image Compression – Vast amounts of information is received and processed
at once by neural networks. This makes them useful in image compression.
With the Internet explosion and more sites using more images on their sites,
using neural networks for image compression is worth a look.
• Stock Exchange Prediction – The day-to-day business of the stock market is
very complicated. Many factors weigh in whether a given stock will go up or
down on any given day. Thus, Neural networks can examine a lot of
information in a fast manner and sort it all out. So we can use them to predict
stock prices.

69. Limitations Of Neural Networks
Enlisted below are some of the drawbacks of Neural
Networks.
• These networks are black boxes for the user as the user
does not have any roles except feeding the input and
observing the output. The user is unaware of the
training happening in the algorithm.
• These algorithms are rather slow and require many
iterations (also called epochs) to give accurate results.
This is because the CPU computes the weights,
activation function of each node separately thereby
making it consume time as well as resources. It also
causes a problem with a large amount of data.

70. Conclusion
• NN falls under machine learning. It is a computational model
composed of multiple neuron nodes. These nodes receive input,
process the input using activation function and pass the output to
the next layers.
• The inputs are associated with connection link weights called
synapse. A basic ANN consists of an input layer, weights, activation
function, hidden layer, and an output layer.
• The activation functions are used to convert the input to the
output. Some of them are binary, bipolar, sigmoid and a ramp
function. There are different types of ANN such as Single-Layer
Feed Forward, Multilayer Feed Forward, Recurrent networks, etc.
based on the number of hidden layers and feedback mechanisms.
• ANN with many hidden layers between the input and output form
deep learning network. The deep learning networks have high
complexity and abstraction level that makes them capable of
computing high dimensional data with thousands of parameters.

71. References
• https://www.softwaretestinghelp.com
• https://medium.com
• Deep learning for healthcare biometrics,
UPENDRA KUMAR , Esha Tripathi , Surya Prakash
Tripathi, 10 pages, IGI Global Publisher, Hershey
PA, USA , 2018, ISBN : 2327-9354.
• https://towardsdatascience.com
• https://analyticsindiamag.com
• https://www.smartsheet.com
• https://missinglink.ai

72. Thank You!