The document provides an overview of various machine learning algorithms and concepts including supervised learning, unsupervised learning, decision trees, statistical learning models, Naive Bayes models, the EM algorithm, and reinforcement learning. It discusses key aspects of each topic such as how supervised learning uses labeled training data while unsupervised learning discovers patterns in unlabeled data. Decision trees use flowcharts to classify data points and statistical learning theory provides a framework for predictive machine learning models.

1. UNIT 4 AI
BY:SURBHI SAROHA

2.  Supervised and unsupervised learning.
 Decision trees.
 Statistical learning model
 Learning with complete data: Naïve Bayes
models
 Learning with hidden data:EM algorithm
 Reinforcement learning

3.  Supervised learning as the name indicates the
presence of a supervisor as a teacher.
 Basically supervised learning is a learning in
which we teach or train the machine using data
which is well labeled that means some data is
already tagged with the correct answer.
 After that, the machine is provided with a new
set of examples(data) so that supervised
learning algorithm analyses the training data(set
of training examples) and produces a correct
outcome from labeled data.

4.  For instance, suppose you are given a basket filled
with different kinds of fruits.
 Now the first step is to train the machine with all
different fruits one by one like this:
 If shape of object is rounded and depression at top
having color Red then it will be labeled as –Apple.
 If shape of object is long curving cylinder having color
Green-Yellow then it will be labeled as –Banana.
 Now suppose after training the data, you have given a
new separate fruit say Banana from basket and asked
to identify it.

5.  Since the machine has already learned the
things from previous data and this time have
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 Banana category.
 Thus the machine learns the things from
training data(basket containing fruits) and
then apply the knowledge to test data(new
fruit).

6.  Supervised learning classified into two
categories of algorithms:
 Classification: A classification problem is
when the output variable is a category, such
as “Red” or “blue” or “disease” and “no
disease”.
 Regression: A regression problem is when
the output variable is a real value, such as
“dollars” or “weight”.

7.  Supervised learning allows collecting data
and produce data output from the previous
experiences.
 Helps to optimize performance criteria with
the help of experience.
 Supervised machine learning helps to solve
various types of real-world computation
problems.

8.  Classifying big data can be challenging.
 Training for supervised learning needs a lot of
computation time. So, it requires a lot of
time.

9.  Unsupervised learning is the training of machine using
information that is neither classified nor labeled and
allowing the algorithm to act on that information
without guidance.
 Here the task of machine is to group unsorted
information according to similarities, patterns and
differences without any prior training of data.
 Unlike supervised learning, no teacher is provided that
means no training will be given to the machine.
 Therefore machine is restricted to find the hidden
structure in unlabeled data by our-self.

10.  For instance, suppose it is given an image having both dogs and
cats which have not seen ever.
 Thus the machine has no idea about the features of dogs and cat
so we can’t categorize it in dogs and cats.
 But it can categorize them according to their similarities,
patterns, and differences i.e., we can easily categorize the above
picture into two parts.
 First first may contain all pics having dogs in it and second part
may contain all pics having cats in it.
 Here you didn’t learn anything before, means no training data or
examples. It allows the model to work on its own to discover
patterns and information that was previously undetected.
 It mainly deals with unlabelled data.

11.  Unsupervised learning classified into two categories
of algorithms:
 Clustering: A clustering problem is where you want to
discover the inherent groupings in the data, such as
grouping customers by purchasing behavior.
 Association: An association rule learning problem is
where you want to discover rules that describe large
portions of your data, such as people that buy X also
tend to buyY.

12.  A decision tree is a decision support tool that uses
a tree-like model of decisions and their possible
consequences, including chance event outcomes,
resource costs, and utility.
 It is one way to display an algorithm that only
contains conditional control statements.
 Decision Tree : Decision tree is the most powerful and
popular tool for classification and prediction.
 A Decision tree is a flowchart like tree structure,
where each internal node denotes a test on an
attribute, each branch represents an outcome of the
test, and each leaf node (terminal node) holds a class
label.

14.  Statistical learning theory is a framework
for machine learning drawing from the fields
of statistics and functional analysis.
 Statistical learning theory deals with the
problem of finding a predictive function
based on data.
 Statistical learning theory has led to
successful applications in fields such
as computer vision, speech recognition,
and bioinformatics.

15.  The goals of learning are understanding and prediction.
 Learning falls into many categories, including supervised
learning, unsupervised learning, online learning,
and reinforcement learning.
 From the perspective of statistical learning theory,
supervised learning is best understood.
 Supervised learning involves learning from a training
set of data.
 Every point in the training is an input-output pair, where
the input maps to an output.
 The learning problem consists of inferring the function
that maps between the input and the output, such that the
learned function can be used to predict the output from
future input.

16.  Naïve Bayes models
 Naïve Bayes Classifier is one of the simple
and most effectiveClassification algorithms
which helps in building the fast machine
learning models that can make quick
predictions.
 It is a probabilistic classifier, which means it
predicts on the basis of the probability of an
object.

17.  Naive Bayes classifiers are a collection of classification algorithms
based on Bayes’Theorem.
 It is not a single algorithm but a family of algorithms where all of
them share a common principle, i.e. every pair of features being
classified is independent of each other.
 Bayes’ theorem finds many uses in the probability theory and
statistics.
 There’s a micro chance that you have never heard about this
theorem in your life.
 Turns out that this theorem has found its way into the world of
machine learning, to form one of the highly decorated algorithms.
 In this article, we will learn all about the Naive Bayes Algorithm,
along with its variations for different purposes in machine
learning.

18.  Naive Bayes is a simple technique for constructing classifiers:
models that assign class labels to problem instances, represented
as vectors of feature values, where the class labels are drawn from
some finite set.
 There is not a single algorithm for training such classifiers, but a
family of algorithms based on a common principle: all naive Bayes
classifiers assume that the value of a particular feature
is independent of the value of any other feature, given the class
variable.
 For example, a fruit may be considered to be an apple if it is red,
round, and about 10 cm in diameter.
 A naive Bayes classifier considers each of these features to
contribute independently to the probability that this fruit is an
apple, regardless of any possible correlations between the color,
roundness, and diameter features.

19.  For some types of probability models, naive Bayes classifiers can be
trained very efficiently in a supervised learning setting.
 In many practical applications, parameter estimation for naive Bayes
models uses the method of maximum likelihood; in other words, one can
work with the naive Bayes model without accepting Bayesian
probability or using any Bayesian methods.
 Despite their naive design and apparently oversimplified assumptions,
naive Bayes classifiers have worked quite well in many complex real-
world situations.
 In 2004, an analysis of the Bayesian classification problem showed that
there are sound theoretical reasons for the apparently
implausible efficacy of naive Bayes classifiers.
 Still, a comprehensive comparison with other classification algorithms in
2006 showed that Bayes classification is outperformed by other
approaches, such as boosted trees or random forests.
 An advantage of naive Bayes is that it only requires a small number of
training data to estimate the parameters necessary for classification

20.  It is a very general algorithm used
to learn probabilistic models in which
variables are hidden; that is, some of the
variables are not observed.
 Models with hidden variables are sometimes
called latent variable models.

21.  In stats, an Expectation–Maximisation (EM) algorithm is
used as an iterative method to know out (local) maximum
likelihood or maximum a posteriori (MAP) estimates of
parameters in statistical models, where the model
depends on unobserved latent variables.
 The EM iteration is used as an alternate between the
performing an expectation (E) step, which creates a
function for the expectation of the log-likelihood
evaluated using the present estimate for the parameters
 It is important for the maximisation (M) step, which help
in computing parameters maximising the expected log-
likelihood found on the E step.These parameter-estimates
are then wont to determine the distribution of the latent
variables within the next E step.

22.  This algorithm is really at the bottom of the
many unsupervised clustering algorithms
within the field of machine learning.
 It was explained, proposed and given its
name during a paper published in 1977 by
Arthur Dempster, Nan Laird and Donald
Rubin. it’s wont to find the local maximum
likelihood parameters of a statistical model
within the cases where latent variables.

24.  It is often wont to fill the missing data during
a sample.
 It is often used because of the basis of
unsupervised learning of clusters.
 It is often used for the aim of estimating the
parameters of the Hidden Markov Model
(HMM).
 It is often used for locating the values of
latent variables.

25.  It has slow convergence.
 It makes convergence to the local optima
only.
 It requires both the possibilities, forward and
backward (numerical optimisation requires
only forward probability).

26.  Reinforcement learning (RL) is an area
of machine learning concerned with
how software agents ought to take actions in
an environment in order to maximize the
notion of cumulative reward.
 Reinforcement learning is one of three basic
machine learning paradigms,
alongside supervised
learning and unsupervised learning.

27.  Reinforcement learning differs from
supervised learning in not needing labelled
input/output pairs be presented, and in not
needing sub-optimal actions to be explicitly
corrected.
 Instead the focus is on finding a balance
between exploration (of uncharted territory)
and exploitation (of current knowledge).

28.  The environment is typically stated in the form
of a Markov decision process (MDP), because
many reinforcement learning algorithms for this
context use dynamic programming techniques.
 The main difference between the classical
dynamic programming methods and
reinforcement learning algorithms is that the
latter do not assume knowledge of an exact
mathematical model of the MDP and they target
large MDPs where exact methods become
infeasible.