You are on page 1of 12

Machine Learning

B.Tech (CSBS) Vth Semester

By:
Prof. Moumita Pal
B.Tech (CSE), M.Tech (CI), Ph.D (pursuing)
Contact No.: +919952038867
Mail id: moumitafdp@gmail.com
Machine Learning Syllabus

Prof. Moumita Pal 2


Contents: Unit 1 Lecture 1

 Introduction to Machine Learning


 What is Machine Learning?
 Relationship between ML and human learning
 How Human Learn?
 How Machines Learn?
 Relationship between AI, ML, DL and DS
 Why Machine Learning?
 Why Now?

Prof. Moumita Pal 3


Introduction to ML

Prof. Moumita Pal 4


What is ML?
It is the field of study that gives computers the capability to learn without being
explicitly programmed.

I/P
Data
Traditional Output
Algorithm Program

I/P
Data
Program
Machine Learning
Output

Prof. Moumita Pal 5


Relationship Between ML and Human Learning

Data Decisions

• https://singularity2030.ch/thoughts-on-human-learning-vs-machine-learning/
• https://www.datasciencecentral.com/profiles/blogs/human-learning-and-
machine-learning-how-they-differ

Prof. Moumita Pal 6


How Human Learn?
1. Remembering/Memorizing defined as the knowing of previously learned material or retrieving, recognizing,
and recalling relevant knowledge.

2. Understanding defined as being able to comprehend facts by comparing and interpreting main ideas within
the learned material.

3. Applying defined as the ability to use learned material in a new or unprompted way of abstraction and to
solve a newly defined problem.

4. Analyzing defined as the ability to examine a problem area and identify the various components (breaking
the problem down).

5. Evaluating defined as the ability to make judgments based on criteria or standards or to combine parts to
form a new concept or idea.

6. Creating defined as the ability to integrate learning from different areas into a plan for solving a problem
and to propose alternative solutions.

Prof. Moumita Pal 7


How Machine Learns?
• In supervised learning the algorithms make predictions based on a set of examples. For instance, historical
stock prices can be used to provide guesses for future prices. Each example used for training is labeled with
the value of interest—in this case the stock price. A supervised learning algorithm looks for patterns in those
value labels. It can use any information that might be relevant—the day of the week, the season, the
company’s financial data, the type of industry or the presence of disruptive geo-political events. After the
algorithm has found the best pattern, it uses that pattern to make predictions like tomorrow’s stock.

• In unsupervised learning data points have no labels associated with them. Instead, the goal of an
unsupervised learning algorithm is to organize the data in some way or to describe its structure. This can
mean grouping it into clusters or finding different ways of looking at complex data so that it appears simpler
or more organized. From that data we might be able to extract knowledge which we were previously unaware
of.

• In reinforced learning the algorithm gets to choose an action in response to each data point. The learning
algorithm also receives a reward signal a short time later, indicating how good the decision was. Based on
this, the algorithm modifies its strategy in order to achieve the highest reward. Reinforcement learning is
common in robotics, where the set of sensor readings at one point in time is a data point, and the algorithm
must choose the robot’s next action.
Prof. Moumita Pal 8
Relationship Between
AI, ML, DL and DS

Prof. Moumita Pal 9


Why Machine Learning?

Prof. Moumita Pal 10


Why Now?

Prof. Moumita Pal 11


Any Questions?

Prof. Moumita Pal 12

You might also like