Introduction to Machine
Learning
What is Machine Learning
Machine learning (ML) is a type of artificial
intelligence (AI) that allows software applications
to become more accurate at predicting outcomes
without being explicitly programmed to do so.
Machine learning algorithms use historical data as
input to predict new output values.
Definition by Tom Mitchell (1998):
Machine Learning is the study of algorithms that
• Improve their performance P
• at some task T
• with experience E. A well-defined learning task is given
by <P,T,E>.
In simple words, the more you learn (through
experience, courses, training or anything else)the more
capable you become at carrying out tasks based on
learning objectives.
So, we can say that performance at given task is
directly proportional to the experience.
P{T} ∝ E
When Do We Use Machine Learning?
ML is used when:
Human expertise does not exist (navigating
on Mars)
Humans can’t explain their expertise (speech
recognition)
Models must be customized (personalized
medicine)
Models are based on huge amounts of data
(genomics)
Working of Machine Learning
Input Data Training Data
Train the Machine
Learning Algorithm
Trained Model
Test the Model with
new input
Is the
No model Yes Machine Learning
performing Model Ready
correctly
Types of Machine Learning
Supervised Learning
Supervised learning is the types of machine
learning in which machines are trained using well
"labelled" training data, and on basis of that data,
machines predict the output. The labelled data
means some input data is already tagged with the
correct output.
Supervised learning is used for classification and
regression.
Supervised Learning
In supervised learning, we require the help of
previously collected data in order to train our
models.
A model based on supervised learning would
require both previous data and the previous
results as input.
By training with this data, the model helps in
predicting results that are more accurate.
Supervised Learning
New input
(What is this)
Unsupervised Learning
Unsupervised learning is a type of machine learning in
which models are trained using unlabeled dataset and
are allowed to act on that data without any supervision.
Unsupervised learning cannot be directly applied to a
regression or classification problem because unlike
supervised learning, we have the input data but no
corresponding output data. The goal of unsupervised
learning is to find the underlying structure of dataset,
group that data according to similarities, and represent
that dataset in a compressed format.
Unsupervised Learning
Unsupervised learning needs no previous data as
input. It is the method that allows the model to
learn on its own using the data, which you give.
Here, the data is not labelled, but the algorithm
helps the model in forming clusters of similar
types of data.
Unsupervised Learning
Example:
Suppose the unsupervised learning algorithm is given an input
dataset containing images of different types of cats and dogs. The
algorithm is never trained upon the given dataset, which means it
does not have any idea about the features of the dataset. The task of
the unsupervised learning algorithm is to identify the image features
on their own. Unsupervised learning algorithm will perform this task
by clustering the image dataset into the groups according to
similarities between images.
Reinforcement Learning
Treat reinforcement learning as learning from
mistake.
The reinforcement learning algorithm work very
similar to how you learn by yourself without any
guidance – basically hit and trial.
When u get something right u get reward and u
move ahead and when u get something wrong, u
get a penalty, u take a step back and then u try to
avoid the incorrect path while exploring another
correct path.
Reinforcement Learning
Reinforcement Learning
States: The observation, the agent does on the
environment after performing an action
Action: An action that the agent performs on the
environment based on its observation
Reward: The feedback the agent receives based
on the action it performed. If the feedback is
positive, it receives a reward and if the feedback is
negative, it receives a punishment.
Challenges in Machine Learning
Data Labelling
Shortage of Experts
Obtaining massive training data sets
Hard to explain problems
Limited possibilities to reuse model
Bias in data and algorithm.
Major Application of Machine
Learning
Medical advancement
E-commerce and Marketing
Financial Sector
Weather Patterns
Media and Entertainment
Comparison between Supervised and
unsupervised learning
Comparison Attribute Supervised Learning Unsupervised Learning
Training dataset Both input and output Only input
contains
Used for Classification and Finding patterns and
Prediction understanding data
Training Data Is Labelled Not labelled
Number of targets Known Beforehand Not known
Feedback from user Provided Not provided
Complexity High Low
Thank you
