Machine learning is an application of artificial

intelligence (AI) that provides systems the ability

to automatically learn and improve from
experience without being explicitly programmed
A classic example of a task that requires machine learning:
It is very hard to say what makes a 2
 TRADITIONAL PROGRAMING VS MACHINE LEARNING

TRADITIONAL PROG. MACHINE LEARNING

 Data and program is run on
the computer to produce the
output.
 Data and output is run on
the computer to create a
program. This program can
be used in traditional
programming.
 Types of Learning
 Supervised (inductive) learning
 Training data includes desired outputs
 Unsupervised learning
 Training data does not include desired outputs
 Semi-supervised learning
 Training data includes a few desired outputs
 Reinforcement learning
 Reinforcement learning is an important type of Machine
Learning where an agent learn how to behave in a
environment by performing actions and seeing the
results.
 Classification
In machine learning classification is the problem of identifying to
which of a set of categories a new observation belongs, on the basis of
a training set of data containing observations

 Example: Credit
scoring Discriminant: IF income > θ1
AND savings > θ2
 Differentiating
THEN low-risk
between low-risk and
high-risk customers ELSE high-risk
from their income
and savings
The benefit of machine learning is that it
can predict

•If you upload a new photo and suddenly it tells you who each person is

•The whole point of machine learning is to predict things based on patterns.

•It can be anything:- housing prices based on zip code , likelihood of a flight delay
based on time of year
MACHINE LEARNING REQUIRE TRAINING

You have to tell a machine learning model what its trying to

predict

Example: face recognition.

 FACE RECOGNITION
 Training examples of a person

•Test images
Some more examples of tasks that are best solved
by using a learning algorithm
 Recognizing patterns:
 Facial identities or facial expressions
 Handwritten or spoken words
 Medical images
 Generating patterns:
 Generating images or motion sequences
 Recognizing anomalies:
 Unusual sequences of credit card transactions
 Unusual patterns of sensor readings in a nuclear power
plant or unusual sound in your car engine.
 Prediction:
 Future stock prices or currency exchange rates
Some web-based examples of machine
learning
 The web contains a lot of data. Tasks with very big datasets
often use machine learning
 especially if the data is noisy or non-stationary.
 Spam filtering, fraud detection:
 The enemy adapts so we must adapt too.
 Recommendation systems:
 Lots of noisy data. Million dollar prize!
 Information retrieval:
 Find documents or images with similar content.
 Data Visualization:
 Display a huge database in a revealing way
Four basic steps used to perform a
machine learning task
• Collecting data: Be it the raw data from excel, access, text files ..
• Training a model: This step involves choosing the appropriate
algorithm and representation of data in the form of the model. The
data is split into two parts – train and test.
1. the first part is training the data 2. The second part is test data.
• Evaluating the model: To check accuracy of model is to see its
performance on data which was not used at a time of training.

• Improving the performance: This step might involve choosing a

different model altogether or introducing more variables to augment
the efficiency. That’s why significant amount of time needs to be
spent in data collection and preparation.
 ML vs AI
 Artificial Intelligence just means a computer that is as
good as (or better than) humans at doing specific
tasks. It can also mean a robot that can make decisions
based on lots of input

 Machine learning is a method for achieving AI. It

means making a prediction about something based on
training from sets of parsed data.