AIES Unit 5 (2022)

School of Computer Engineering & Technology.
T. Y. B. Tech.
(Computer)
Unit 5 –
Advanced topics
and Applications
of AI
Syllabus
Introduction to Artificial Intelligence and Search Strategies
01
History and Introduction to AI, Intelligent Agent, Types of agents, Environment and types,
Typical AI problems
Search Strategies: Problem solving and formulating a problem State Space Search -
Uninformed and Informed Search Techniques, Heuristic function, A*, AO* algorithms ,Hill
climbing, simulated annealing, genetic algorithms ,Constraint satisfaction method
Game Playing: Minimax algorithm, alpha beta cut offs
Knowledge Representation and Planning
02 Propositional logic and predicate logic, Knowledge Representation structure such as frame,
Conceptual dependencies, Semantic networks and script, Resolution in predicate logic,
Unification algorithm, Forward and Backward chaining, Logic Programming
Planning: Forward and Backward planning, Goal Stack Planning, Hierarchical Planning.
Knowledge Inference and Expert System
03 Basics of Probability, Statistical reasoning, Bayes' Theorem, Bayesian learning and network
Expert systems: Architecture of Expert system, Role of Expert system, Inference engine,
Knowledge acquisition, Typical Expert systems- MYCIN, Expert systems shells.
Advanced topics and Applications of AI

04 Applications of AI , Artificial Neural Network, Deep learning, Fuzzy logic, Natural Language
Processing, Introduction to Machine Learning, Introduction to Robotics and Computer Vision,
Applications of AI in Business.
2
• https://youtu.be/Pq6Rdf7Va4c (application of AI)
• https://youtu.be/nOnsbd7rdhc (application of AI)
• https://youtu.be/Ta_vWUsrjho (neuron)
• https://youtu.be/bfmFfD2RIcg (ANN)
• https://youtu.be/6M5VXKLf4D4 (deep learning)
• https://youtu.be/WSbgixdC9g8 (AI vs deep learning vs Machine learning)
• https://youtu.be/w-8MTXT_N6A (AI vs deep learning vs Machine learning)
• https://youtu.be/rln_kZbYaWc (fuzzy logic)
• https://youtu.be/d4gGtcobq8M (NLP)
• https://youtu.be/ukzFI9rgwfU (Machine Learning)
• https://youtu.be/OOfXhz4In_w (Robotics)
• https://youtu.be/OcycT1Jwsns (computer vision )
• https://youtu.be/YOEFogy9VSQ ( AI in business)
3
Applications of AI
✔ There are several fields where AI is helping human beings to solve real
life problems effectively and accurately.
✔ There are various domains in which AI applications are playing
significant role. Today, many thousands of AI applications are deeply
embedded in the infrastructure of every industry.
✔ Following are domains and few examples

✔ Marketing Gaming
✔ Banking Space exploration
✔ Finance Autonomous Vehicles
✔ Agriculture Chatbots
✔ Healthcare SocialMedia…
4
Applications of AI (Cntd.)
✔ Marketing – to attract the customer based on their likeliness, experience, requirements etc.
build bots or autonomous systems that provides highly accurate predictions, suggestions
based on customer’s reactions. For example,
□ Netflix – finding the right movies, to suggest shows and films that you might like based
on your previous actions and choices of films.
□ Amazon – finding the right products, to suggest products that you might like based on
your previous actions and choices of products.
✔ Banking – to fulfill various customer related services completing their requirements. A lot
of banks have already adopted AI-based systems to provide customer support, detect
anomalies and credit card frauds. For example,
□ HDFC Bank – developed an AI-based chatbot called EVA (Electronic Virtual Assistant).
□ MasterCard and RBS WorldPay – have relied on AI and Deep Learning to detect
fraudulent transaction patterns and prevent card fraud for years now.
5
✔ Finance – to determine future patterns in the market. Trading mainly depends on the
ability to predict the future accurately. Machines are great at this because they can crunch a
huge amount of data in a short span. Machines can also learn to observe patterns in past
data and predict how these patterns might repeat in the future. In the age of ultra-high-
frequency trading, financial organizations are turning to AI to improve their stock trading
performance and boost profit. For example,
□ Nomura Securities – Japan’s leading brokerage house. The company has been
reluctantly pursuing one goal, i.e. to analyze the insights of experienced stock traders
with the help of computers.
6
✔ Agriculture – Issues such as climate change, population growth, and food security concerns
have pushed the industry into seeking more innovative approaches to improve crop yield as the
world will need to produce 50 percent more food by 2050. AI can help farmers get more from
the land while using resources more sustainably. For example,
□ Organizations are using automation and robotics to help farmers find more efficient ways
to protect their crops from weeds. Blue River Technology has developed a robot called
See & Spray which uses computer vision technologies like object detection to
monitor and precisely spray weedicide on cotton plants. Precision spraying can help
prevent herbicide resistance.
□ Apart from this, Berlin-based agricultural tech start-up called PEAT, has developed an
application called Plantix that identifies potential defects and nutrient deficiencies
in the soil through images. The image recognition app identifies possible defects through
images captured by the user’s smartphone camera. Users are then provided with soil
restoration techniques, tips, and other possible solutions. The company claims that its
software can achieve pattern detection with an estimated accuracy of up to 95%.
7
✔ Healthcare – When it comes to saving our lives, a lot of organizations and medical care
centers are relying on AI. There are many examples of how AI in healthcare has helped
patients all over the world. For example,
□ An organization called Cambio Health Care developed a clinical decision support
system for stroke prevention that can give the physician a warning when there’s a
patient at risk of having a heart stroke.
□ Another such example is Coala life which is a company that has a digitalized device
that can find cardiac diseases.
□ Similarly, Aifloo is developing a system for keeping track of how people are doing in
nursing homes, home care, etc.
The best thing about AI in healthcare is that you don’t even need to develop a new
medication. Just by using an existing medication in the right way, you can also save lives.
8
✔ Gaming – Over the past few years, Artificial Intelligence has become an integral part of the
gaming industry. In fact, one of the biggest accomplishments of AI is in the gaming industry.
For example,
□ DeepMind’s AI-based AlphaGo software, which is known for defeating Lee Sedol, the
world champion in the game of GO, is considered to be one of the most significant
accomplishment in the field of AI.
□ IBM's DEEP BLUE became the first computer program to defeat the world champion in
a chess match when it defeated Garry Kasparov by a score of 3.5 to 2.5 in an exhibition
match.
□ IBM Watson is a question-answering computer system capable of answering questions
posed in natural language. Watson computer system competed on Jeopardy! against
champions Brad Rutter and Ken Jennings, winning the first place prize of $1 million.
9
✔ Gaming – (Cntd.)
□ Other examples of Artificial Intelligence in gaming include the First Encounter Assault
Recon, popularly known as F.E.A.R, which is a first-person shooter video game. But
what makes this game so special? The actions taken by the opponent AI are
unpredictable because the game is designed in such a way that the opponents are
trained throughout the game and never repeat the same mistakes. They get better as
the game gets harder.
□ Few more example include S.T.A.L.K.E.R. Series, Far Cry 2, StarCraft 2 and
□ Halo: Combat evolved game – A first-person shooter game assumes the role of the
Master Chief, battling various aliens on foot or in vehicles. Enemies use cover very
wisely, and employ suppressing fire and grenades. The squad situation affects the
individuals, so certain enemies flee when their leader dies. A lot of attention is paid to
the little details, with enemies notably throwing back grenades or team-members
responding to you bothering them. The underlying "behavior tree" technology has
become very popular in the games industry (especially since Halo 2).
10
✔ Space Exploration – Space expeditions and discoveries always require analyzing vast
amounts of data. Artificial Intelligence and Machine learning is the best way to handle and
process data on this scale. For Example,
□ After rigorous research, astronomers used Artificial Intelligence to sift through years of
data obtained by the Kepler telescope in order to identify a distant eight-planet solar
system.
□ Artificial Intelligence is also being used for NASA’s next rover mission to Mars, the Mars
2020 Rover. The AEGIS, which is an AI-based Mars rover is already on the red planet.
The rover is responsible for autonomous targeting of cameras in order to perform
investigations on Mars.
□ A hundred million miles from Earth, NASA's Remote Agent program became the first
on-board autonomous planning program to control the scheduling of operations for a
spacecraft. Successor program MAPGEN plans the daily operations for NASA's Mars
Exploration Rovers, and MEXAR2 did mission planning both logistics and science
planning for the European Space Agency's Mars Express mission in 2008.
11
✔ Autonomous Vehicles – For the longest time, self-driving cars have been a buzzword in the
AI industry. The development of autonomous vehicles will definitely revolutionaries the
transport system. AI have contributed to the growth of the automotive industry through the
creation and evolution of self-driving vehicles. As of 2016, there are over 30 companies
utilizing AI into the creation of self-driving cars. A few companies involved with AI
include Tesla, Google, and Apple.
□ Companies like Waymo conducted several test drives in Phoenix before deploying their
first AI-based public ride-hailing service. The AI system collects data from the vehicles
radar, cameras, GPS, and cloud services to produce control signals that operate the
vehicle. Advanced Deep Learning algorithms can accurately predict what objects in the
vehicle’s vicinity are likely to do. This makes Waymo cars more effective and safer.
□ Another famous example of an autonomous vehicle is Tesla’s self-driving car.
Artificial Intelligence implements computer vision, image detection and deep learning
to build cars that can automatically detect objects and drive around without human
intervention.
12
✔ Chatbots – These days Virtual assistants have become a very common technology. Almost
every household has a virtual assistant that controls the appliances at home. A few
examples include Siri, Cortana, which are gaining popularity because of the user
experience they provide.
□ Amazon’s Echo is an example of how Artificial Intelligence can be used to translate
human language into desirable actions. This device uses speech recognition and NLP to
perform a wide range of tasks on your command. It can do more than just play your
favorite songs. It can be used to control the devices at your house, book cabs, make
phone calls, order your favorite food, check the weather conditions and so on.
□ Another example is the newly released Google’s virtual assistant called Google Duplex,
that has astonished millions of people. Not only can it respond to calls and book
appointments for you, but it also adds a human touch. The device uses Natural language
processing and machine learning algorithms to process human language and perform
tasks such as manage your schedule, control your smart home, make a reservation and
so on.
13
✔ Social media – Ever since social media has become our identity, we’ve been generating an
immeasurable amount of data through chats, tweets, posts and so on. And wherever there is
an abundance of data, AI and Machine Learning are always involved.
□ In social media platforms like Facebook, AI is used for face verification wherein
machine learning and deep learning concepts are used to detect facial features and tag
your friends. Deep Learning is used to extract every minute detail from an image by
using a bunch of deep neural networks. On the other hand, Machine learning
algorithms are used to design your feed based on your interests.
□ Another such example is Twitter’s AI, which is being used to identify hate speech and
terroristic language in tweets. It makes use of Machine Learning, Deep Learning, and
Natural language processing to filter out offensive content. The company discovered
and banned 300,000 terrorist-linked accounts, 95% of which were found by non-
human, artificially intelligent machines.
14
✔ Artificial Creativity – Have you ever wondered what would happen if an artificially
intelligent machine tried to create music and art?
□ An AI-based system called MuseNet can now compose classical music that echoes the
classical legends, Bach and Mozart. MuseNet is a deep neural network that is capable of
generating 4-minute musical compositions with 10 different instruments and can
combine styles from country to Mozart to the Beatles. MuseNet was not explicitly
programmed with an understanding of music, but instead discovered patterns of
harmony, rhythm, and style by learning on its own.
□ Another creative product of Artificial Intelligence is a content automation tool called
WordSmith. WordSmith is a natural language generation platform that can transform
your data into insightful narratives. Tech giants such as Yahoo, Microsoft, Tableau, are
using WordSmith to generate around 1.5 billion pieces of content every year.
15
✔ Spam fighting – Each day, learning algorithms classify over a billion messages as spam,
saving the recipient from having to waste time deleting what, for many users, could
comprise 80% or 90% of all messages, if not classified away by algorithms. Because the
spammers are continually updating their tactics, it is difficult for a static programmed
approach to keep up, and learning algorithms work best.
✔ Logistics planning – During the Persian Gulf crisis of 1991, U.S. forces deployed a Dynamic
Analysis and Replanning Tool (DART), to do automated logistics planning and scheduling
for transportation. This involved up to 50,000 vehicles, cargo, and people at a time, and had
to account for starting points, destinations. routes, and conflict resolution among all
parameters. The AI planning techniques generated in hours a plan that would have taken
weeks with older methods. The Defense Advanced Research Project Agency (DARPA) stated
that this single application more than paid back DARPA's 30-year investment in Al.
16
✔ Robotics – The iRobot Corporation has sold over two million Roomba robotic vacuum
cleaners for home use. The company also deploys the more rugged PackBot to Iraq and
Afghanistan, where it is used to handle hazardous materials, clear explosives, and identify
the location of snipers. Hanson Robotics is building humanoid robots with artificial
intelligence for both the commercial and consumer markets. The Hanson-created Sophia is
an incredibly advanced social-learning robot. Through AI, Sophia can efficiently
communicate with natural language and use facial expressions to convey human-like
emotions.
17
Artificial Neural Network [ANN]
✔ History of ANN:
□ History of the ANNs stems from the 1940s, the decade of the first electronic computer.
□ However, the first important step took place in 1957 when Rosenblatt introduced the
first concrete neural model, the perceptron. Rosenblatt also took part in constructing
the first successful neurocomputer, the Mark I Perceptron. After this, the development
of ANNs has proceeded as described in Figure.
18
Artificial Neural Network [ANN] (Cntd.)
✔ History of ANN (Cntd.):
□ Rosenblatt's original perceptron model contained only one layer. From this, a
multi-layered model was derived in 1960. At first, the use of the multi-layer
perceptron (MLP) was complicated by the lack of a appropriate learning
algorithm.
□ In 1974, Werbos came to introduce a so-called back propagation algorithm for the
three-layered perceptron network.
19
□ in 1986, The application area of the MLP networks remained rather limited until the
breakthrough when a general back propagation algorithm for a multi-layered perceptron
was introduced by Rummelhart and Mclelland.
□ in 1982, Hopfield brought out his idea of a neural network. Unlike the neurons in MLP, the
Hopfield network consists of only one layer whose neurons are fully connected with
each other.
20
□ Since then, new versions of the Hopfield network have been developed.
□ The Boltzmann machine has been influenced by both the Hopfield network and
the MLP.
21
□ in 1988, Radial Basis Function (RBF) networks were first introduced by Broomhead
& Lowe.
□ Although the basic idea of RBF was developed 30 years ago under the name method of
potential function, the work by Broomhead & Lowe opened a new frontier in the neural
network community.
22
□ in 1982, A totally unique kind of network model is the Self-Organizing Map (SOM)
introduced by Kohonen. SOM is a certain kind of topological map which organizes itself
based on the input patterns that it is trained with.
□ The SOM originated from the LVQ (Learning Vector Quantization) network the
underlying idea of which was also Kohonen's in 1972.
23
□ Since then, research on artificial neural networks has remained active, leading to many
new network types, as well as hybrid algorithms and hardware for neural information
processing.
An artificial neural network consists of a pool of simple processing units which

communicate by sending signals to each other over a large number of weighted
connections.
24
✔ How Brain works?
□ We have discussed briefly on the basic findings of neuroscience—in particular, the
hypothesis that mental activity consists primarily of electrochemical activity in
networks of brain cells called neurons. Following showed a schematic diagram of a
typical neuron.
Dendrites: Input Cell

body: Processor
Synaptic: Link
Axon: Output
25
✔ How Brain works? (Cntd.)
□ The Brain is a massively parallel information processing system.
□ Our brains are a huge network of processing elements. A typical brain contains a
network of 10 billion neurons.
26
✔ How Brain works? (Cntd.)
□ A neuron is connected to other neurons through about 10,000
synapses.
□ A neuron receives input from other neurons. Inputs are
combined.
□ Once input exceeds a critical level, the neuron discharges a spike -
an electrical pulse that travels from the body, down the axon, to
the next neuron(s)
□ The axon endings almost touch the dendrites or cell body of the
next neuron.
□ Transmission of an electrical signal from one neuron to the next is
effected by neurotransmitters.
□ Neurotransmitters are chemicals which are released from the first
neuron and which bind to the Second.
□ This link is called a synapse. The strength of the signal that
reaches the next neuron depends on factors such as the amount of
neurotransmitter available. 27
✔ How do ANN works?
□ An artificial neural network (ANN) is either a hardware implementation or a
computer program which strives to simulate the information processing capabilities
of its biological exemplar.
□ ANNs are typically composed of a great number of interconnected artificial neurons.
The artificial neurons are simplified models of their biological counterparts.
□ ANN is a technique for solving problems by constructing software that works like our
brains.
28
✔ How do ANN works? (Cntd.)
□ An artificial neuron is an imitation of a human
neuron
29
□ Now, let us have a look at the model of an artificial
neuron.
30
□ Neural networks have lots of pieces, and to refer to them we will need to introduce a variety of
mathematical notations. Following Table lists all notations used
31
□ The basic unit of computation in a neural network is the neuron, often called a node or
unit. Following figure shows a Unit in Neural network.
32
Input ............
Processing
Output y
33
............
Input
Weight .....
Not all inputs are equal s

Processing ∑
Output y
34
............
Input
Weight .....
The signal is not s

passed down to the Processing ∑
next neuron verbatim
Transfer Function
(Activation Function)
Output y
35
Perceptron:
□ A perceptron is a neural network unit (an artificial neuron) that does certain
computations to detect features or business intelligence in the input data.
□ Perceptron is usually used to classify the data into two parts. Therefore, it is also
known as a Linear Binary Classifier. Also, it is used in supervised learning. It helps to
classify the given input data.
□ Perceptron is a single layer neural network and a multi-layer perceptron is called
Neural Networks.
□ There are two types of Perceptrons: Single layer and Multilayer.
▪ Single layer Perceptrons can learn only linearly separable patterns.
▪ Multilayer Perceptrons or feed forward neural networks with two or more
layers have the greater processing power.
36
Structure of Perceptron:
37
Multilayer Perceptron:
The output is a function

of the input, that is
affected by the weights,
and the transfer functions
38
✔ Comparison between brain verses computer
Brain ANN
Speed Few ms. Few nano sec. massive parallel
processing
Size and 1011 neurons & 1015 interconnections Depends on designer
complexity
Storage capacity Stores information in its interconnection Contiguous memory locations
or in synapse. loss of memory may happen sometimes.
No Loss of memory
Tolerance Has fault tolerance No fault tolerance If gets disrupted when
interconnections are disconnected
Control Complicated involves chemicals in Simpler in ANN
mechanism biological neuron
39
✔ McCulloch-Pitts Neuron Model
40
✔ Basic models of ANN
Basic Models of
ANN
Activation
Interconnections Learning rules
function
41
✔ Activation Function:
□ The purpose of the activation function is to introduce non-linearity into the output of a
neuron.
Name Equation Plot Range
Linear or Identity Function
Binary Step function
Bipolar Step function
Logistic (a.k.a. Sigmoid or

Soft step)
TanH (a.k.a. Tangent
Hyperbolic function)
42
✔ Activation Function: (cntd.)
□ The purpose of the activation function is to introduce non-linearity into the output of a
neuron.
Name Equation Plot Range
Rectified linear unit
(ReLU)
Ramp Function
43
✔ Interconnection:
Interconnections
Feed forward Feed Back Recurrent
Single layer Single layer
Multilayer Multilayer
44
✔ Interconnection: (Cntd.)
□ Single Layer Feed Forward Network
▪ A layer is formed by taking a
processing element and combining it
with other processing elements. When
a layer of the processing nodes is
formed, the inputs can be connected to
these nodes with various weights,
resulting in a series of outputs, one per
node. Thus, a single layer feed forward
network is formed.
45
□ Multilayer feed forward network
▪ A multilayer feed forward network is formed by the interconnection of several
layers. The input layer is that which receives the input and this layer has no
function except buffering the input signal. The output layer generates the output of
the network. Any layer that is formed between the input layer and the output layer
is called the hidden layer.
▪ Can be used to solve complicated problems.
46
□ Feedback network
▪ When outputs are directed back as inputs to same or preceding layer nodes it
results in the formation of feedback networks.
47
□ Lateral feedback
▪ If the feedback of the output of the processing elements is directed back as input to
the processing elements in the same layer then it is called lateral feedback.
48
□ Recurrent network
▪ Feedback networks with closed loop are called Recurrent Networks.
▪ Recurrent neural network is a class of artificial neural network where connections
between nodes form a directed graph along a sequence. This allows it to exhibit
dynamic temporal behavior for a time sequence. Unlike feed forward neural
networks, RNNs can use their internal state (memory) to process sequences of
inputs.
1. Single node with own feedback
2. Competitive networks
3. Single-layer recurrent networks
4. Multilayer recurrent networks
5. Jordan Network
49
□ Recurrent network (Cntd.)
▪ Single node with own

feedback
50
▪ Fully recurrent network (Competitive networks)

It is the simplest neural network architecture because all nodes are connected to all other
nodes and each node works as both input and output.
51
▪ Single-layer recurrent network

This network is single layer network with
feedback connection in which processing
element’s output can be directed back to
itself or to other processing element or both.
52
▪ Multi-layer recurrent network

In this type of network, processing element output
can be directed to the processing element in the
same layer and in the preceding layer forming a
multilayer recurrent network.
They perform the same task for every element of a
sequence, with the output being depended on the
previous computations.
Inputs are not needed at each time step.
The main feature of an Recurrent Neural Network is
its hidden state, which captures some information
about a sequence.
53
▪ Jordan network
It is a closed loop network in which the output will go to the input again as feedback as shown
in the following diagram.
54
✔ Learning:
□ It’s a process by which a NN adapts itself to a stimulus by making proper parameter
adjustments, resulting in the production of desired response
□ Two kinds of learning
1. Parameter learning:- connection weights are updated
2. Structure Learning:- change in network structure
55
✔ Classification of learning
1. Supervised learning
2. Unsupervised learning
3. Reinforcement learning
56
✔ Classification of learning (Cntd.)
1. Supervised learning
▪ Child learns from a teacher
▪ Each input vector requires a corresponding target vector.
▪ Training pair=[input vector, target vector]
Neural
X Network Y
W
(Input) (Actual output)
(D-Y)
Error
Error Signal D
signals Generator (Desired Output)
57
✔ Classification of learning (Cntd.)
1. Supervised learning (Cntd.)
▪ Supervised learning does minimization of error
58
✔ Classification of learning (Cntd)
2. Unsupervised learning
▪ How a fish or tadpole learns
▪ All similar input patterns are grouped together as clusters.
▪ If a matching input pattern is not found a new cluster is formed
59
✔ Classification of learning (Cntd)
2. Unsupervised learning (Cntd.)
▪ In unsupervised learning there is no feedback
▪ Network must discover patterns, regularities, features for the input data over
the output
▪ While doing so the network might change in parameters
▪ This process is called self-organizing
60
3. Reinforcement
learning
Y
X NN
W (Actual output)
Error
signals Error
Signal R
Generator Reinforcement signal
61
3. Reinforcement learning (Cntd.)
▪ When Reinforcement learning is used?
• If less information is available about the target output values (critic
information)
• Learning based on this critic information is called reinforcement learning
and the feedback sent is called reinforcement signal
• Feedback in this case is only evaluative and not instructive
62
✔ Example learning algorithms
□ Supervised:
▪ Adaline, Madaline
▪ Perceptron
▪ Back Propagation
▪ Multilayer perceptrons
▪ Radial Basis Function Networks
□ Unsupervised
▪ Competitive Learning
▪ Kohenen self organizing map
▪ Learning vector quantization
▪ Hebbian learning
63
Deep Learning
✔ Deep learning is a branch of machine learning which is completely based on artificial neural
networks, as neural network is going to mimic the human brain so deep learning is also a
kind of mimic of human brain. In deep learning, we don’t need to explicitly program
everything.
✔ Definition: Deep learning is a particular kind of machine learning that achieves great
power and flexibility by learning to represent the world as a nested hierarchy of concepts,
with each concept defined in relation to simpler concepts, and more abstract
representations computed in terms of less abstract ones.
64
Deep Learning (Cntd.)
✔ Architectures :
□ Deep Neural Network – It is a neural network with a certain level of complexity (having
multiple hidden layers in between input and output layers). They are capable of
modeling and processing non-linear relationships.
□ Deep Belief Network(DBN) – It is a class of Deep Neural Network. It is multi-layer belief
networks. Steps for performing DBN :
1. Learn a layer of features from visible units using Contrastive Divergence algorithm.
2. Treat activations of previously trained features as visible units and then learn
features of features.
3. Finally, the whole DBN is trained when the learning for the final hidden layer is
achieved.
□ Recurrent (perform same task for every element of a sequence) Neural Network – Allows
for parallel and sequential computation. Similar to the human brain (large feedback
network of connected neurons). They are able to remember important things about the
input they received and hence enables them to be more precise.
65
✔ Difference Between ML and DL:
MACHINE LEARNING DEEP LEARNING

Works on small amount of Dataset for accuracy. Works on Large amount of Dataset.
Dependent on Low-end Machine. Heavily dependent on High-end Machine.
Divides the tasks into sub-tasks, solves them
individually and finally combine the results. Solves problem end to end.
Takes less time to train. Takes longer time to train.

Testing time may increase. Less time to test the data.
66
✔ Working:
67
✔ Advantages :
□ Best in-class performance on problems.
□ Reduces need for feature engineering.
□ Eliminates unnecessary costs.
□ Identifies defects easily that are difficult to detect.
✔ Disadvantages :
□ Large amount of data required.
□ Computationally expensive to train.
□ No strong theoretical foundation.
68
✔ Applications :
□ Automatic Text Generation
□ Healthcare
□ Automatic Machine Translation
□ Image Recognition
□Predicting Earthquakes
And many more…
69
Fuzzy Logic
✔ The term fuzzy refers to things which are not clear or are vague. In the real world many
times we encounter a situation when we can’t determine whether the state is true or false,
their fuzzy logic provides a very valuable flexibility for reasoning. In this way, we can
consider the inaccuracies and uncertainties of any situation.
✔ In boolean system truth value, 1.0 represents absolute truth value and 0.0 represents
absolute false value. But in the fuzzy system, there is no logic for absolute truth and
absolute false value. But in fuzzy logic, there is intermediate value too present which is
partially true and partially false.
70
Fuzzy Logic (Cntd.)
✔ Architecture:
Rule Base
Fuzzifier Defuzzifier
Inferenc
e
Engine
71
Fuzzy Logic (Cntd.)
✔ Advantages of Fuzzy Logic System:
□ This system can work with any type of inputs whether it is imprecise, distorted or noisy
input information.
□ The construction of Fuzzy Logic Systems is easy and understandable.
□ Fuzzy logic comes with mathematical concepts of set theory and the reasoning of that is
quite simple.
□ It provides a very efficient solution to complex problems in all fields of
life as it resembles human reasoning and decision making.
□ The algorithms can be described with little data, so little memory is required.
72
Fuzzy Logic (Cntd.)
✔ Disadvantages of Fuzzy Logic System:
□ Many researchers proposed different ways to solve a given problem through fuzzy logic
which lead to ambiguity. There is no systematic approach to solve a given problem
through fuzzy logic.
□ Proof of its characteristics is difficult or impossible in most cases because every time
we do not get mathematical description of our approach.
□ As fuzzy logic works on precise as well as imprecise data so most of the time accuracy
is compromised.
73
Fuzzy Logic (Cntd.)
✔ Applications:
□ It is used in the aerospace field for altitude control of spacecraft and satellite.
□ It has used in the automotive system for speed control, traffic control.
□ It is used for decision making support systems and personal evaluation in the large
company business.
□ It has application in chemical industry for controlling the pH, drying,
chemical distillation process.
□ Fuzzy logic are used in Natural language processing and various intensive applications
in Artificial Intelligence.
□ Fuzzy logic are extensively used in modern control systems such as expert systems.
□ Fuzzy Logic is used with Neural Networks as it mimics how a person would make
decisions, only much faster. It is done by Aggregation of data and changing into more
meaningful data by forming partial truths as Fuzzy sets.
74
Natural Language Processing
✔ Brief History of NLP
□ 1940s –1950s: Foundations
• Development of formal language theory (Chomsky, Backus, Naur, Kleene)
• Probabilities and information theory (Shannon)
□ 1957 – 1970s:
• Use of formal grammars as basis for natural language processing (Chomsky, Kaplan)
• Use of logic and logic based programming (Minsky, Winograd, Colmerauer, Kay)
□ 1970s – 1983:
• Probabilistic methods for early speech recognition (Jelinek, Mercer)
□ 1983 – 1993:
• Finite state models (morphology) (Kaplan, Kay)
□ 1993 – 1995:
• Strong integration of different techniques, different areas.
• 1997 - LSTM recurrent neural net (RNN) models were introduced
• 2001 - Yoshio Bengio and his team proposed the first neural “language” model, using a feed-forward neural
network.
• 2011 - Apple’s Siri became known as one of the world’s first successful NLP/AI assistants to be used by
general consumers.
75
Natural Language Processing (Cntd.)
✔ Working of NLP:
□ NLP breaks down language into shorter, more basic pieces, called tokens (words,
periods, etc.), and attempts to understand the relationships of the tokens. This process often
uses higher-level NLP features, such as:
□ Content Categorization: A linguistic document summary that includes content alerts,
duplication detection, search, and indexing.
□ Topic Discovery and Modeling: Captures the themes and meanings of text collections, and
applies advanced analytics to the text.
□ Contextual Extraction: Automatically pulls structured data from text-based sources.
□ Sentiment Analysis: Identifies the general mood, or subjective opinions, stored in large
amounts of text. Useful for opinion mining.
□ Text-to-Speech and Speech-to-Text Conversion: Transforms voice commands into text, and
vice versa.
□ Document Summarization: Automatically creates a synopsis, condensing large amounts of
text.
□ Machine Translation: Automatically translates the text or speech of one language into
another.
76
✔ Knowledge Representation for NLP:
□ Which knowledge representation will be used depends on the application -- Machine
Translation, Database Query System.
□ Requires the choice of representational framework, as well as the specific meaning
vocabulary (what are concepts and relationship between these concepts -- ontology)
□ Must be computationally effective.
□ Common representational formalisms:
▪ first order predicate logic
▪ conceptual dependency graphs
▪ semantic networks
▪ Frame-based representations
77
✔ The process of computer analysis of input provided in a human language (natural
language), and conversion of this input into a useful form of representation.
✔ The field of NLP is primarily concerned with getting computers to perform useful and
interesting tasks with human languages.
✔ The field of NLP is secondarily concerned with helping us come to a better understanding of
human language.
78
✔ Forms of Natural Language:
□ The input/output of a NLP system can be:
▪ written text
▪ speech
□ We will mostly concerned with written text (not speech).
□ To process written text, we need:
▪ lexical, syntactic, semantic knowledge about the language
▪ discourse information, real world knowledge
□ To process spoken language, we need everything required to process written text, plus
the challenges of speech recognition and speech synthesis.
79
✔ Components of NLP:
□ Natural Language Understanding
▪ Mapping the given input in the natural language into a useful representation.
▪ Different level of analysis required:
• morphological analysis,
• syntactic analysis,
• semantic analysis,
• discourse analysis, …
□ Natural Language Generation
▪ Producing output in the natural language from some internal representation.
▪ Different level of synthesis required:
• deep planning (what to say),
• syntactic generation
□ NL Understanding is much harder than NL Generation. But, still both of them are hard.
80
✔ Natural Language Understanding:
□ Taking some spoken/typed sentence and working out what it means
✔ Natural Language Generation:
□ Taking some formal representation of what you want to say and working out a way to
express it in a natural (human) language (e.g., English)
81
✔ Natural Language Understanding:
Raw speech signal

• Speech recognition
Sequence of words spoken

• Syntactic analysis using knowledge of the grammar
Structure of the sentence

• Semantic analysis using info. about meaning of words
Partial representation of meaning of sentence

• Pragmatic analysis using info. about context
Final representation of meaning of sentence
82
✔ Natural Language Understanding: (Cntd.)
Input/Output data Processing stage
Other data used
Frequency spectrogram freq. of diff.
speech recognition sounds
Word sequence grammar of
“He loves Mary” syntactic analysis language
Sentence structure meanings of
semantic analysis words

He loves Mary
Partial Meaning context of
Ξx loves(x,mary) pragmatics utterance
Sentence meaning
loves(john,mary)
83
✔ Steps in NLP:
84
✔ Natural Language Generation (NLG):
□ NLG is the process of constructing natural language outputs from non-linguistic inputs.
□ NLG can be viewed as the reverse process of NL understanding.
□ A NLG system may have two main parts:
▪ Discourse Planner -- what will be generated. which sentences.
▪ Surface Realizer -- realizes a sentence from its internal representation.
□ Lexical Selection -- selecting the correct words describing the concepts.
□ Traditional approach to NLG involves following steps:
▪ Document Planning
▪ Micro planning
▪ Surface realization
▪ Final Presentation
85
✔ NLG System Architecture:
Control
Data
Input Output
Data Document Micro Data
Realization
Planning -planning
Content Lexical Choice

Determination Referring
Expressions
Document
Structuring Aggregation
86
✔ Applications of NLG:
□ Present information in more convenient way
▪ Airline schedule database
▪ Accounting spreadsheet
□ Automating document production
▪ Doctor writing discharge summaries
▪ Programmer writing code documentation, logic description etc.
□ In many contexts, human intervention is required to create texts
□ NLG system is used to produce an initial draft of a document which can be further
edited by human author. E.g.
▪ Weather Reporter, which helps meteorologists compose weather forecasts
▪ DRAFTER, which helps technical authors write software manuals
▪ AlethGen, which helps customer-service representatives write response letters to
customers
87
Introduction to Machine Learning
✔ The term Machine Learning was coined by Arthur Samuel in 1959, an American pioneer in
the field of computer gaming and artificial intelligence and stated that “it gives computers
the ability to learn without being explicitly programmed”.
✔ And in 1997, Tom Mitchell gave a “well-posed” mathematical and relational definition that,
“A computer program is said to learn from experience E,
with respect to some task T,
and some performance measure P,
if its performance on T, as measured by P, improves with experience E.
88
✔ (Cntd.)
Classification of Machine Learning:
□ Supervised Learning
□ Unsupervised Learning
□ Reinforcement Learning
□ Semi-supervised Learning
✔ Classification of Machine Learning on the basis of required Output:
□ Another categorization of machine learning tasks arises when one considers the desired output
of a machine-learned system:
▪ Classification : When inputs are divided into two or more classes, and the learner must produce a
model that assigns unseen inputs to one or more (multi-label classification) of these classes. This is
typically tackled in a supervised way. Spam filtering is an example of classification, where the inputs
are email (or other) messages and the classes are “spam” and “not spam”.
▪ Regression : Which is also a supervised problem, A case when the outputs are continuous rather than
discrete.
▪ Clustering : When a set of inputs is to be divided into groups. Unlike in classification, the groups are
not known beforehand, making this typically an unsupervised task.
89
✔ (Cntd.)
Key Differences between AI and ML:
ARTIFICIAL INTELLIGENCE MACHINE LEARNING
AI stands for Artificial intelligence, where intelligence is defined

acquisition of knowledge intelligence is defined as a ability to ML stands for Machine Learning which is defined as the acquisition
acquire and apply knowledge. of knowledge or skill
The aim is to increase chance of success and not accuracy. The aim is to increase accuracy, but it does not care about success
It work as a computer program that does smart work It is a simple concept machine takes data and learn from data.
The goal is to learn from data on certain task to maximize the

The goal is to simulate natural intelligence to solve complex problem performance of machine on this task.
AI is decision making. ML allows system to learn new things from data.
It leads to develop a system to mimic human to respond behave in a

circumstances. It involves in creating self learning algorithms.
AI will go for finding the optimal solution. ML will go for only solution for that whether it is optimal or not.
AI leads to intelligence or wisdom. ML leads to knowledge.

90
Introduction to Robotics
✔ Robotics is a branch of engineering andscience that includes electronics
engineering, mechanical engineering and computer science and so on.
✔ This branch deals with the design, construction, use to control robots, sensory feedback and
information processing.
91
Introduction to Robotics (Cntd.)
✔ Characteristics of Robot:
□ Appearance: Robots have a physical body. They are held by the structure of their body and are
moved by their mechanical parts. Without appearance, robots will be just a software program.
□ Brain: Another name of brain in robots is On-board control unit. Using this robot receive information
and sends commands as output. With this control unit robot knows what to do else it’ll be just a
remote-controlled machine.
□ Sensors: The use of these sensors in robots is to gather info from the outside world and send it to
Brain. Basically, these sensors have circuits in them that produces the voltage in them.
□ Actuators: The robots move and the parts with the help of these robots move is called Actuators.
Some examples of actuators are motors, pumps, and compressor etc. The brain tells these actuators
when and how to respond or move.
□ Program: Robots only works or responds to the instructions which are provided to them in the form
of a program. These programs only tell the brain when to perform which operation like when to
move, produce sounds etc. These programs only tell the robot how to use sensors data to make
decisions.
□ Behavior: Robots behavior is decided by the program which has been built for it. Once the robot
starts making the movement, one can easily tell which kind of program is being installed inside92 the
robot.
✔ Advantages of using Robots:
□ They can get information that a human can’t get.
□ They can perform tasks without any mistakes and very efficiently and fast.
□ Maximum robots are automatic, so they can perform different tasks without needing human interaction.
□ Robots are used in different factories to produce items like plane, car parts etc.
□ They can be used for mining purposes and can be sent to earth’s nadris.
✔ Disadvantages of using Robots:
□ They need the power supply to keep going. People working in factories may lose their jobs as robots can
replace them.
□ They need high maintenance to keep them working all day long. And the cost of maintaining the robots
can be expensive.
□ They can store huge amount of data but they are not as efficient as our human brains.
□ As we know that robots work on the program that has been installed in them. So other than the
program installed, robots can’t do anything different.
□ The most important disadvantage is that if the program of robots comes in wrong hands they can cause
the huge amount of destruction.
93
✔ Applications using Robots:
□ Robots are increasingly been used more than humans in manufacturing while in auto-industry there are
more than half of the labors are “Robots”.
□ Many of the robots are used as Military Robots.
□ Robots have been used in cleaning up of areas like toxic waste or industrial wastes etc.
□ Agricultural robots.
□ Household robots.
□ Domestic robots.
□ Nano robots.
□ Swarm robots.
94
Introduction to Computer Vision
✔ Computer Vision, often abbreviated as CV, is defined as a field of study that seeks to develop
techniques to help computers “see” and understand the content of digital images such as
photographs and videos.
✔ At an abstract level, the goal of computer vision problems is to use the observed image data
to infer something about the world.
✔ It is a multidisciplinary field that could broadly be called a subfield of artificial intelligence
and machine learning, which may involve the use of specialized methods and make use of
general learning algorithms.
95
Introduction to Computer Vision (Cntd.)
✔ Application:
□ Laptop: Biometrics auto-login (face recognition, 3D), OCR
□ Smartphones: QR codes, computational photography (Android Lens Blur, iPhone Portrait Mode), panorama
construction (Google Photo Spheres), face detection, expression detection (smile), Snapchat filters (face tracking),
Google Tango (3D reconstruction), Night Sight (Pixel)
□ Web: Image search, Google photos (face recognition, object recognition, scene recognition, geolocalization from
vision), Facebook (image captioning), Google maps aerial imaging (image stitching), YouTube (content
categorization)
□ VR/AR: Outside-in tracking (HTC VIVE), inside out tracking (simultaneous localization and mapping, HoloLens),
object occlusion (dense depth estimation)
□ Motion: Kinect, full body tracking of skeleton, gesture recognition, virtual try-on
□ Medical imaging: CAT / MRI reconstruction, assisted diagnosis, automatic pathology, connectomics, endoscopic
surgery
□ Industry: Vision-based robotics (marker-based), machine-assisted router (jig), automated post, ANPR (number
plates), surveillance, drones, shopping
□ Transportation: Assisted driving (everything), face tracking/iris dilation for drunkeness, drowsiness, automated
distribution (all modes)
□ Media: Visual effects for film, TV (reconstruction), virtual sports replay (reconstruction), semantics-based auto
edits (reconstruction, recognition)
96
Quick Questions
✔ List and explain applications of Artificial Intelligence.
✔ List and explain applications of Robotics.
✔ List and explain applications of Computer Vision.
✔ Compare between Human Brain and Artificial Neural Network.
✔ Write detailed note on how ANN works.
✔ Discuss in detail Activation Functions used in ANN.
✔ Discuss with neat diagrams various interconnections used in ANN.
✔ Write a short note on Classification of Learning in ANN.
✔ Compare between ML and DL.
✔ Compare between AI, ML and DL.
✔ Explain advantages and disadvantages of deep learning along with various applications of DL.
✔ Explain advantages and disadvantages of Fuzzy Logic along with various applications of Fuzzy Logic.
✔ Discuss in detail components of NLP.
✔ Explain advantages and disadvantages of NLP along with various applications of NLP.
✔ Compare AI with ML.
✔ Discuss Applications of Computer Vision.
97
Reference
✔ s Intelligence: A Modern Approach”, Third
Stuart Russell and Peter Norvig, “Artificial
edition, Pearson, 2013
✔ E. Rich and K.Knight, Artificial Intelligence, Tata McGraw Hill, 1992.
✔ Tom Mitchell , Machine Learning, McGraw hill publication
✔ Ethem Alpaydin, “ Introduction to Machine Learning”, PHI 2nd Edition-2013, ISBN
978-0-262-01243-0
98

AIES Unit 5 (2022)

Uploaded by

Copyright:

Available Formats

AIES Unit 5 (2022)

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

AIES Unit 5 (2022)

Uploaded by

Copyright:

Available Formats

School of Computer Engineering & Technology.

Knowledge Representation and Planning

Knowledge Inference and Expert System

Advanced topics and Applications of AI

✔ Following are domains and few examples

An artificial neural network consists of a pool of simple processing units which

Dendrites: Input Cell

Not all inputs are equal s

The signal is not s

The output is a function

Linear or Identity Function

Binary Step function

Bipolar Step function

Logistic (a.k.a. Sigmoid or

Feed forward Feed Back Recurrent

Single layer Single layer

▪ Single node with own

▪ Fully recurrent network (Competitive networks)

▪ Single-layer recurrent network

▪ Multi-layer recurrent network

MACHINE LEARNING DEEP LEARNING

Takes less time to train. Takes longer time to train.

Raw speech signal

Sequence of words spoken

Structure of the sentence

Partial representation of meaning of sentence

Final representation of meaning of sentence

semantic analysis words

Content Lexical Choice

AI stands for Artificial intelligence, where intelligence is defined

The goal is to learn from data on certain task to maximize the

AI is decision making. ML allows system to learn new things from data.

It leads to develop a system to mimic human to respond behave in a

AI leads to intelligence or wisdom. ML leads to knowledge.

You might also like