Subject Coordinator : Aakanksha Agrawal

Contents
⚫Syllabus
⚫Text Books
⚫Course Outcomes
⚫Unit-1
Syllabus
 Text Books
1)Tom M. Mitchell, ―Machine Learning, McGraw-Hill Education (India)
Private Limited, 2013.
2)Ethem Alpaydin, ―Introduction to Machine Learning (Adaptive
Computation and Machine Learning), The MIT Press 2004.
3)Stephen Marsland, ―Machine Learning: An Algorithmic
Perspective, CRC Press, 2009.
4)Bishop, C., Pattern Recognition and Machine Learning. Berlin:
Springer-Verlag
Course Outcomes
- Mark Cuban, American entrepreneur
What is Machine Learning?
What is Machine Learning?
 What is Machine Learning?
⚫The term Machine learning was first introduced by Arthur Samuel in
1959.
⚫ Artificial Intelligence is the concept of creating smart intelligent machines.
⚫ Machine Learning is a subset of artificial intelligence that helps you build
AI-driven applications.
⚫ Deep Learning is a subset of machine learning that uses vast volumes of
data and complex algorithms to train a model.
⚫ As intelligence requires knowledge, it is necessary for the computers to
acquire knowledge.
 Machine Learning Definition

⚫ “Machine learning refers to a system capable of the autonomous

acquisition and integration of knowledge.”

⚫“Machine Learning enables a machine to automatically learn from

data, improve performances from experiences, and predict things
without explicitly programmed.”
⚫Let’s have a look at an example of an AI-driven product-
Amazon Echo :
How Does Machine Learning Work?
⚫ Machine learning accesses vast amounts of data (both structured and
unstructured) and learns from it to predict the future. It learns from the
data by using multiple algorithms and techniques.
 ML Applications & Examples
1) Social Media Features : E.g : Facebook notices & records your
activities, chats, likes, and comments, and the time you spend on
specific kinds of posts. ML learns from your own experience & makes
friend page suggestions for your profile.
2) Product Recommendations Using ML & AI, websites track your
behavior based on your previous purchases, searching patterns, and
cart history, and then make product recommendations.
3) Image Recognition : Image recognition is an approach for cataloging
and detecting a feature or an object in the digital image.
4) Sentiment Analysis : It is a real-time ML application that determines
the emotion or opinion of the speaker or the writer. For e.g, if someone
has written a review or email (or any form of a document), a sentiment
analyzer will instantly find out the actual thought and tone of the text.
5)Language Translation : One of the most common ML applications is
language translation. It plays a significant role in the translation of one
language to another. E.g: websites can translate from one language to
another effortlessly.
6) Medical diagnosis :
Real-world examples for medical diagnosis:
⚫ Assisting in formulating a diagnosis or recommends a treatment option
⚫ Oncology & pathology use ML to recognise cancerous tissue
Types of ML
 1) Supervised Learning
⚫ In supervised learning technique, we train the machines using the
"labelled" dataset, and based on the training, the machine
predicts the output
⚫ The labelled data specifies that some of the inputs are already
mapped to the output.
⚫ First, we train the machine with the input & corresponding output,
and then we ask the machine to predict the output using the test
dataset.
Supervised Learning Techniques
Supervised machine learning can be classified into two types of problems,
which are given below:
1) Classification A classification problem is when the output variable is a
category, such as “Red” or “blue” , “disease” or “no disease”.
Some popular classification algorithms are given below:
⚫ Random Forest Algorithm
⚫ Decision Tree Algorithm (ID3)
⚫ Naïve Bayes Algorithm
⚫ Support Vector Machine Algorithm
 Supervised Learning
2) Regression A regression problem is when the output variable is a
real value, such as “dollars” or “weight”.
Techniques of Regression :

⚫ Simple Linear Regression Algorithm

⚫ Multivariate Regression Algorithm
Supervised Learning Example
⚫ Suppose you are given a basket filled with different kinds of fruits.
Supervised Learning Example
⚫ Now the first step is to train the machine with all the different fruits
one by one like this:
⚫ If the shape of the object is rounded and has a depression at the
top, is red in color, then it will be labeled as –Apple.
⚫ If the shape of the object is a long curving cylinder having Green-
Yellow color, then it will be labeled as – Banana.
⚫ Now suppose after training the data, you have given a new separate
fruit, say Banana from the basket, and asked to identify it.
Supervised Learning Example
⚫ Since the machine has already learned the things from previous data
and this time has to use it wisely. It will first classify the fruit with its
shape and color and would confirm the fruit name as BANANA and put
it in the Banana category. Thus the machine learns the things from
training data(basket containing fruits) and then applies the knowledge
to test data(new fruit).
Advantages and Disadvantages
Supervised Learning
⚫Advantages:-
1. Supervised learning allows collecting data and produces data output
from previous experiences.
2. Helps to optimize performance criteria with the help of experience.
3. Supervised machine learning helps to solve various types of real-
world computation problems.
⚫Disadvantages:-
1. Classifying big data can be challenging.
2. Training for supervised learning needs a lot of computation time.
So, it requires a lot of time.
 2) Unsupervised Learning
⚫ The main aim of the unsupervised learning algorithm is to group or
categories the unsorted dataset according to the similarities, patterns,
and differences.
⚫ Unsupervised Learning can be further classified into two types, which
are given below:

1) Clustering: Some of the popular clustering algorithms are given below:

⚫ K-Means Clustering algorithm
⚫ Mean-shift algorithm
⚫ DBSCAN Algorithm
⚫ Principal Component Analysis

2) Association Rule Mining

 Unsupervised Learning
Example
⚫ Suppose machine is given an image having both dogs and cats which it has
never seen.
Unsupervised Learning Example

⚫ Machine categorizes them according to their similarities, patterns

and differences, i.e., we can easily categorize the above picture into
two parts.
⚫ First may contain all pics having dogs in them and
⚫ second part may contain all pics having cats in them.
⚫ Here you didn’t learn anything before, which means no training data or
examples.
 Advantages and Disadvantages
Unsupervised Learning
⚫ Advantages:-
1. Unsupervised learning is used for more complex tasks as compared to supervised
learning because, in unsupervised learning, we don't have labeled input data.
2. Unsupervised learning is preferable as it is easy to get unlabeled data in comparison to
labeled data.
Disadvantages:-
1. Unsupervised learning is intrinsically more difficult than supervised learning as it does
not have corresponding output.
2. The result of the unsupervised learning algorithm might be less accurate as input data is
not labeled, and algorithms do not know the exact output in advance.
 Quiz

⚫ Identify whether given scenarios uses Supervised or

Unsupervised Learning ?
A) FB Face Recognition
B) Netflix Recommends Movies
C) Analysing Fraud Detection
 3) Reinforcement Learning
⚫ Reinforcement Learning is a feedback-based ML technique in which an
agent learns to behave in an environment by performing the actions and
seeing the results of actions.
⚫ For each good action, the agent gets positive feedback, and for
each bad action, the agent gets negative feedback or penalty.
⚫ The agent learns automatically using feedbacks without any labeled
data, unlike supervised learning.
⚫ E.g : Game-playing, Robotics, etc.
 Reinforcement Learning
⚫ How a Robotic dog learns the movement of his arms is an e.g of
Reinforcement learning.
⚫ Let's take an example of a maze environment that the agent
needs to explore.
⚫ Environment: It can be anything such as a room, maze,
football ground, etc.
⚫ Agent: An intelligent agent such as AI robot.
Reinforcement Learning
 Reinforcement Learning
Example
⚫ Let’s say you have a dog and you are trying to train your dog to sit.
 Reinforcement Learning
Example
⚫ You would give certain instructions to the dog to try to make it learn. If the
dog executes the instruction perfectly, it would get a biscuit as a reward. If
not, it would not get anything. The dog learns from this after some tries that it
would get a biscuit if it sits.

⚫ This is what the gist of reinforcement learning is. The reward here is the
feedback received by the dog for sitting. This algorithm has various
applications in real life.

⚫ It is helpful in making self-driving cars.

 Terms used in Reinforcement
Learning
⚫ Agent (): An entity that can perceive/explore the environment and act upon it.
⚫ Environment (): A situation in which an agent is present or surrounded by. In RL, we
assume the stochastic environment, which means it is random in nature.
⚫ Action (): Actions are the moves taken by an agent within the environment.
⚫ State (): State is a situation returned by the environment after each action taken by the
agent.
⚫ Reward (): A feedback returned to the agent from the environment to evaluate the
action of the agent.
⚫ Policy (): Policy is a strategy applied by the agent for the next action based on the
current state.
 Advantages and Disadvantages of
Reinforcement Learning
⚫Advantages
Reinforcement learning is used to solve complex problems that cannot be solved by
conventional techniques. This learning model is very similar to the learning of human
beings. Hence, it is close to achieving perfection.

⚫Disadvantages
Too much reinforcement learning can lead to an overload of states which can diminish the
results, also it is not preferable for solving simple problems. The curse of dimensionality
limits reinforcement learning for real physical systems.
 Issues in Machine Learning
1. Data quality. Machine learning systems rely on data. ...

2. The complexity and quality trade-off. ...

3. Sampling bias in data. ...

4. Changing expectations and concept drift. ...

5. Monitoring and maintenance.

6. Data Collection. Data plays a key role in any use case. ...

7. Less Amount of Training Data. ...

 Issues in Machine Learning
8. Non-representative Training Data. ...

9. Poor Quality of Data. ...

10. Irrelevant/Unwanted Features. ...

11. Overfitting the Training Data. ...

12. Under fitting the Training data. ...

13. Offline Learning & Deployment of the model.

 Well Posed Learning Problem
⚫ A computer program is said to learn from experience E with respect to
some class of tasks T and performance measure P, if its performance
in tasks T, as measured by P, improves with experience E.
⚫ Any problem can be segregated as well-posed learning problem if it
has three traits –
a) Task
b) Performance Measure
c) Experience
Well Posed Learning Problem E.g
⚫ Certain examples that efficiently defines the well- posed learning
problem are –
⚫ 1) A checkers learning problem :
⚫ Task – Playing checkers game
⚫ Performance Measure – % of games won against opponent
⚫ Experience – playing implementation games against itself
Well Posed Learning Problem E.g
2) Fruit Prediction Problem
⚫ Task – forecasting different fruits for recognition
⚫ Performance Measure – able to predict maximum variety of fruits
⚫ Experience – training machine with the largest datasets of fruits images

3) Face Recognition Problem

⚫ Task – predicting different types of faces
⚫ Performance Measure – able to predict maximum types of faces
⚫ Experience – training machine with maximum amount of datasets of
different face images
Designing a Learning System
⚫For any learning system, we must be knowing the three
elements — T (Task), P (Performance Measure), and E
(Training Experience).
⚫Learning process starts with task T, performance measure P and
training experience E and objective is to find an unknown target
function. The target function is an exact knowledge to be
learned from the training experience and its unknown.
⚫For example, in a case of credit approval,
Experience : Customer application records
Task : To classify whether the given customer application is
eligible for a loan.
So in this case, the training examples can be represented as
(x1,y1)(x2,y2)..(xn,yn) where X represents customer
application details and y represents the status of credit
approval.
Designing a Learning System
⚫Target function to be learned in the credit approval learning
system is a mapping function f:X →y. This function represents
the exact knowledge defining the relationship between input
variable X and output variable y.
⚫Next, the learning algorithms try to guess a “hypothesis’’
function h(X) that approximates the unknown f(.). A
hypothesis is a function that best describes the target &
hypothesis set is the collection of all the possible legal
hypothesis. This is the set from which the ML algorithm would
determine the best possible (only one) which would best
describe the target function or the outputs. The goal of the
learning process is to find the final hypothesis that best
approximates the unknown target function.
Designing a Learning System
Designing a Learning System
⚫We will look into the checkers learning problem and apply the
above design choices. For a checkers learning problem, the three
elements will be,
⚫1. Task T: To play checkers
2.Performance measure P: Total % of the game won in the
tournament.
3.Training experience E: A set of games played against itself
1) Choosing Training Experience
a)Direct or Indirect Feedback
⚫ Direct : Individual checkers board states & correct moves
for each
⚫ Indirect : Moves sequences & final outcome of various
games
⚫ Learner faces problem of ‘Credit Assignment’
b) Degree to which learner controls sequence of
training examples
c)How well it represents distribution of e.g’s over which
Final system performance will be measured
E.g –Checkers Game
⚫Task T: playing checkers
⚫ Performance measure P: percent of games won in
the world tournament
⚫ Training experience E: games played against
itself
2) Choosing Target Function
⚫To determine exactly what type of knowledge will
be learned and how this will be used by the
performance program
⚫E.g : checkers-playing program that can generate
the legal moves from any board state. The
program needs only to learn how to choose the
best move from among these legal moves.
⚫ chooseMove V : BM where B : Legal Board state
M : set of real no’s
 Choosing Target Function
⚫What should be the value of V for any board state?
a) If b is a final board state that is won then V(b)= 100
b) if b is a final board state that is lost, then V(b) = -100
c) if b is a final board state that is drawn, then V(b) = 0
d) if b is a not a final state in the game, then V(b) =
V(b’), where b' is the best final board state that can be
achieved starting from b and playing optimally until
the end of the game
3) ChoosingRepresentation for Target
Function
⚫Allow program to represent using a large table with a
distinct entry specifying the value for each distinct board
state.
⚫ To represent using a collection of rules that match against
features of the board state, or
⚫a quadratic polynomial function of predefined board
features, or Artificial neural network
Choosing Representation for Target
Function
⚫E.g In Checkers Problem, for any given board state, the
function V will be calculated as a linear combination of the
following board features:
Xl: the number of black pieces on the board X2: the
number of red pieces on the board X3: the number of
black kings on the board X4: the number of red kings on
the board
X5: the number of black pieces threatened by red (i.e., which can
be captured on red's next turn)
X6: the number of red pieces threatened by black
Choosing Representation for Target
Function
⚫ Thus, our learning program will represent V(b) as a
linear function of the form :

where Wo through W6 are numerical coefficients, or

weights, to be chosen by the learning algorithm.
Learned values for the weights Wl through W6 will
determine the relative importance of the various board
features in determining the value of the board
4) Choosing a Function Approximation
Algorithm
⚫ To learn a Target Function f, we need a set of Training
Examples.
⚫ Training Example Representation :
⚫ Ordered Pair= (b, Vtrain(b) )
⚫ E.g : Black won the game
⚫ X2= 0, Vtrain(b) = +100
⚫ b= (X1=3,X2=0,X3=1,X4=0,X5=0,X6=0)
<(X1=3,X2=0,X3=1,X4=0,X5=0,X6=0) +100>
Choosing a Function Approximation
Algorithm
⚫ There are 2 steps in this phase :
a) Estimating the Training Values :
Vtrain(b)  V^(successor (b))
where V^ represents learners current approximation to V
It estimates that this move will help/destroy opponent.
b) Adjusting the weights :
We use LMS (Least Mean Square )
 5) Final Design
The final design of our checkers learning system can be naturally described by four distinct program
modules that represent the central components in many learning systems. These four modules
1.Performance System: Solve performance task using learned target function(s). It takes instance of new
problem as input and a trace of its solution (history) as output.

2.Critic: Take history of problem as input and produce a set of training examples of target function as
output.
3.Generalizer: Take training examples as input and produce estimate of target function as output
hypothesis. It generalizes from specific training examples, hypothesizing a general function that covers all
examples.
4.Experiment Generator: Take current hypothesis (currently learned function) as input and outputs a new
problem (i.e., initial board state) for Performance System to explore. Its role is to pick new practice
problems that will maximize the learning rate of the overall system.
Final Design
Traditional Programing VS ML