Revision Questions and answers

ARTIFICIAL INTELLIGENCE SYSTEMS;

1. a) What is intelligence in AI?

Artificial intelligence (AI) is the ability of a computer or a robot controlled by a
computer to do tasks that are usually done by humans because they require human
intelligence and discernment.
b. List x-tics of intelligence in AI?

 Feature Engineering. ...

 Artificial Neural Networks. ...
 Deep Learning. ...
 Natural language processing. ...
 Intelligent Robotics. ...
 Perception. ...
 Automate Simple and Repetitive Tasks. ...
2. a) Differentiate with examples traditional programming and artificial intelligence?
Traditional computer programming has been around for more than a century, with the first
known computer program dating back to the mid-1800s. Traditional
Programming refers to any manually created program that uses input data and runs on
a computer to produce the output.

But for decades now, an advanced type of programming has revolutionized business,
particularly in the areas of intelligence and embedded analytics. In Machine
Learning programming, also known as augmented analytics, the input data and output
are fed to an algorithm to create a program. This yields powerful insights that can be used
to predict future outcomes.

Here’s a closer comparison of traditional programming versus machine learning:

Traditional Programming
Traditional programming is a manual process—meaning a person (programmer) creates
the program. But without anyone programming the logic, one has to manually formulate
or code rules.

In machine learning, on the other hand, the algorithm automatically formulates the rules
from the data.

Machine Learning Programming

Unlike traditional programming, machine learning is an automated process. It can
increase the value of your embedded analytics in many areas, including data prep, natural
language interfaces, automatic outlier detection, recommendations, and causality and
significance detection. All of these features help speed user insights and reduce decision
bias.

For example, if you feed in customer demographics and transactions as input data and
use historical customer churn rates as your output data, the algorithm will formulate a
program that can predict if a customer will churn or not. That program is called
a predictive model.
You can use this model to predict business outcomes in any situation where you have
input and historical output data:

1. Identify the business question you would like to ask.

2. Identify the historical input.

3. Identify the historically observed output (i.e., data samples for when the condition
is true and for when it’s false).

For instance, if you want to predict who will pay the bills late, identify the input (customer
demographics, bills) and the output (pay late or not), and let the machine learning use
this data to create your model.

As you can see, machine learning can turn your business data into a financial asset. You
can point the algorithm at your data so it can learn powerful rules that can be used to
predict future outcomes. It’s no wonder predictive analytics is now the number one
capability on product roadmaps.

b) Discuss any two areas in our daily life where artificial intelligence is used?

Self-driving Vehicles

The technology of Autonomous Vehicle AI is witnessing large-scale innovation

driven by global corporate interest. AI is making innovations beyond cruise control
and blind-spot detection to include fully autonomous capabilities.

Deep Reinforcement Learning (DRL), a subset of machine learning, is being

applied to teach vehicles to operate independently. Path planning in the face of
static and dynamic obstacles is being made possible through various predictive AI
models.

Predicting accurately when neighboring vehicles will swerve and other such
unforeseen events are being taken into account. Simultaneous Localization and
Mapping (SLAM) is the technology that makes this possible with real-time
orientation to surroundings via sensors.

Facial Recognition Technologies

The most popular application of this technology is the Face ID unlock feature in
most of the flagship smartphone models today. The biggest challenge faced by
this technology is widespread concern around the racial and gender bias of its use
in forensics.

Generative Adversarial Neural Networks (GANN) are being applied to reduce the
margin of error in facial recognition software. These neural networks are also being
trained to pinpoint the unethical use of Deep fake technology.
 Various industries are also developing AI software that picks up facial expressions
to identify mood and intention. Emotion AI or Affective Computing is an emerging
area of interest to gauge customer experience.

3a. Give 5 branches of AI?

 Machine Learning.
 Deep Learning.
 Natural Language Processing.
 Robotics.
 Expert Systems.
 Fuzzy Logic.
b. Choose anyone of the above topics and discuss its fundamental concepts?
4a. Discuss the benefits of Artificial Neural Networks (ANN) and give a practical application in
real life?

ANNs have the ability to learn and model non-linear and complex relationships, which is really
important because in real-life, many of the relationships between inputs and outputs are non-linear
as well as complex.

2. ANNs can generalize — After learning from the initial inputs and their relationships, it can infer
unseen relationships on unseen data as well, thus making the model generalize and predict on
unseen data.

Unlike many other prediction techniques, ANN does not impose any restrictions on the input
variables (like how they should be distributed). Additionally, many studies have shown that ANNs
can better model heteroscedasticity i.e. data with high volatility and non-constant variance, given
its ability to learn hidden relationships in the data without imposing any fixed relationships in the
data. This is something very useful in financial time series forecasting (e.g. stock prices) where data
volatility is very high.

Application

Forecasting: Forecasting is required extensively in everyday business decisions (e.g. sales,

the financial allocation between products, capacity utilization), in economic and monetary policy,
finance, and the stock market. More often, forecasting problems are complex, for example,
predicting stock prices is a complex problem with a lot of underlying factors (some known, some
unseen). Traditional forecasting models throw up limitations in terms of taking into account these
complex, non-linear relationships. ANNs, applied in the right way, can provide a robust alternative,
given their ability to model and extract unseen features and relationships. Also, unlike these
traditional models, ANN doesn’t impose any restrictions on input and residual distributions.
More research is going on in the field, for example — recent advances in the usage of LSTM and
Recurrent Neural Networks for forecasting.

ANNs are powerful models that have a wide range of applications. Above, I have listed a few
prominent ones, but they have far-reaching applications across many different fields in medicine,
security, banking/finance as well as government, agriculture, and defense.

In my next post, I’ll explore a bit more about the usage of ANN for time series forecasting.

5a. What do you understand by the following terms;

 Artificial intelligence? AI which stands for artificial intelligence refers to systems or

machines that mimic human intelligence to perform tasks and can iteratively improve
themselves based on the information they collect.

 Machine Learning? the use and development of computer systems that are able to learn
and adapt without following explicit instructions, by using algorithms and statistical
models to analyze and draw inferences from patterns in data.

 Fuzzy Logic? is a logic or control system of an n-valued logic system that uses the degrees
of state “degrees of truth “of the inputs and produces outputs that depend on the states of
the inputs and the rate of change of these states (rather than the usual “true or false” (1 or
0), Low or High Boolean logic (Binary) on which the modern computer is based).

6. Write short notes on the following;

I. Supervised Learning? Supervised learning uses a training set to teach models to yield the
desired output. This training dataset includes inputs and correct outputs, which allow the model
to learn over time. The algorithm measures its accuracy through the loss function, adjusting until
the error has been sufficiently minimized.
II. Reinforcement Learning? Reinforcement learning is an area of Machine Learning. It is
about taking suitable action to maximize reward in a particular situation. It is employed by
various software and machines to find the best possible behavior or path it should take in a specific
situation.

iii. Unsupervised Learning? Unsupervised learning refers to the use of artificial intelligence
(AI) algorithms to identify patterns in data sets containing data points that are neither
classified nor labeled.

7a. What do you understand by artificial neurons? An artificial neuron is a connection point in
an artificial neural network. Artificial neural networks, like the human body's biological neural
network, have a layered architecture and each network node (connection point) has the capability
to process input and forward output to other nodes in the network.

b. Compare and contrast biological neurons and artificial neurons?

Comparison Chart

BASIS FOR ARTIFICIAL BIOLOGICAL NEURAL

COMPARISON NEURAL NETWORK NETWORK

Processing Sequential and Parallel and distributed

centralized

Rate Artificial neural Biological neurons are slow in

networks process processing information.

 BASIS FOR ARTIFICIAL BIOLOGICAL NEURAL

COMPARISON NEURAL NETWORK NETWORK

information at a faster

pace.

Size Small Large

Complexity Incapable to perform The enormous size and complexity

complex pattern of the connections provide the brain

recognition. with the capability the perform

complex tasks.

Fault tolerance Intolerant to the failure. Implicitly fault-tolerant.

Control mechanism The Control unit All the processing is centrally

monitors all computing- controlled.

related activities.

Feedback Not provided Provided

8. Discuss with examples the Regression and Classification process in machine learning?

Regression and Classification algorithms are Supervised Learning algorithms. Both the algorithms
are used for prediction in Machine learning and work with the labeled datasets. But the difference
between both is how they are used for different machine learning problems.

The main difference between Regression and Classification algorithms is that Regression
algorithms are used to predict the continuous values such as price, salary, age, etc., and
Classification algorithms are used to predict/Classify the discrete values such as Male or Female,
True or False, Spam or Not Spam, etc.

Consider the below diagram:

Classification:
Classification is a process of finding a function that helps in dividing the dataset into classes based
on different parameters. In Classification, a computer program is trained on the training dataset,
and based on that training, it categorizes the data into different classes.

The task of the classification algorithm is to find the mapping function to map the input(x) to the
discrete output(y).

Example: The best example to understand the Classification problem is Email Spam Detection.
The model is trained on the basis of millions of emails on different parameters, and whenever it
receives a new email, it identifies whether the email is spam or not. If the email is spam, then it is
moved to the Spam folder.
Types of ML Classification Algorithms:

Classification Algorithms can be further divided into the following types:

o Logistic Regression
o K-Nearest Neighbors
o Support Vector Machines
o Kernel SVM
o Naïve Bayes
o Decision Tree Classification
o Random Forest Classification

Regression:

Regression is the process of finding the correlations between dependent and independent variables.
It helps in predicting the continuous variables such as prediction of Market Trends, prediction of
House prices, etc.

The task of the Regression algorithm is to find the mapping function to map the input variable(x)
to the continuous output variable(y).

Example: Suppose we want to do weather forecasting, so for this, we will use the Regression
algorithm. In weather prediction, the model is trained on the past data, and once the training is
completed, it can easily predict the weather for future days.

Types of Regression Algorithm:

o Simple Linear Regression

o Multiple Linear Regression
o Polynomial Regression
o Support Vector Regression
o Decision Tree Regression
o Random Forest Regression

Difference between Regression and Classification

Regression Algorithm Classification Algorithm

In Regression, the output variable must be of continuous In Classification, the output variable must be a
nature or real value. discrete value.

The task of the regression algorithm is to map the input The task of the classification algorithm is to map the
value (x) with the continuous output variable(y). input value(x) with the discrete output variable(y).

Regression Algorithms are used with continuous data. Classification Algorithms are used with discrete data.

In Regression, we try to find the best fit line, which can In Classification, we try to find the decision
predict the output more accurately. boundary, which can divide the dataset into different
classes.

Regression algorithms can be used to solve the Classification Algorithms can be used to solve
regression problems such as Weather Prediction, House classification problems such as Identification of
price prediction, etc. spam emails, Speech Recognition, Identification of
cancer cells, etc.

The regression Algorithm can be further divided into The Classification algorithms can be divided into
Linear and Non-linear Regression. Binary classifiers and Multi-class classifiers.

9a. Discuss the concept of fuzzy logic? Fuzzy logic is an approach to variable processing that
allows for multiple possible truth values to be processed through the same variable. Fuzzy logic
attempts to solve problems with an open, imprecise spectrum of data and heuristics that makes it
possible to obtain an array of accurate conclusions.
b. Give three areas where fuzzy logic is applied with one example each? Fuzzy logic has been used
in numerous applications such as facial pattern recognition, air conditioners, washing machines,
vacuum cleaners, antiskid braking systems, transmission systems, control of subway systems and
unmanned helicopters, and knowledge-based systems for multi-objective optimization of power
systems.
c. Draw the fuzzy logic systems architecture?

10. Write short notes on the following terms related to AI;

 i) Artificial neuron? Artificial neurons (also called perceptrons, Units, or Nodes) are the
simplest elements or building blocks in a neural network. They are inspired by biological
neurons that are found in the human brain. A biological neuron receives its input signals from
other neurons through dendrites (small fibers). Likewise, a perceptron receives its data from
other perceptrons through input neurons that take numbers.

ii) AI technique? There are four types summarized as follows;

 iii) Learning? Machine learning is an application of AI that enables systems to learn and improve
from experience without being explicitly programmed. Machine learning focuses on developing
computer programs that can access data and use it to learn for themselves. The machine learning
process begins with observations or data, such as examples, direct experience, or instruction. It
looks for patterns in data so it can later make inferences based on the examples provided. The
primary aim of ML is to allow computers to learn autonomously without human intervention or
assistance and adjust actions accordingly.
As a discipline, machine learning explores the analysis and construction of algorithms that
can learn from and make predictions on data.

iv) Applications of AI?

 Travel & Navigation.

 Smartphone Apps.
 Social Media Feeds.
 Advertisements.
 Smart Cars.
 Music and Video Streaming.
 Smart Home.
 Smart Input.