presentation

1. Presented by:-
Prity Mahato(ECE/401/19L)
2018-2022
𝟒 𝒕𝒉 𝑺𝒆𝒎

2. CONTENT
• What is machine learning?
• Why machine learning now a tech buzz?
• Types of machine learning
• Supervised learning
• Unsupervised learning
• Reinforcement learning
• Steps to solve a machine learning problem
• Application of machine learning
• Growth of machine learning
• Future scope
• Conclusion
• E-certificate
• References

3. WHAT IS MACHINE LEARNING?
• An exciting and potentially far-reaching development in computer
science is the invention and application of methods of machine learning
(ML).
• This crystallized information can then be used to automatically make
predictions or to help people make decisions faster and more accurately.
“Machine Learning: Field of study that gives computers the
ability to learn without being explicitly programmed. In
1959, Quoted By- Arthur Samuel”
Using data for answering questions
Training Predicting

4. Why Machine Learning Now a Tech Buzz?
Big Data Faster processor

5. TYPES OF MACHINE LEARNING
• Supervised
Learning
Unsupervised
Learning
Reinforcement
Learning
Classification Regression Clustering
Collaborative
Filtering
Spam/No
Spam
House Rate
Prediction
Social
Network
Analysis
Amazon
/Netflix
Recommenda
tions

6. Supervised Learning
• The set of data (training data) consists of a set of input data
and correct responses corresponding to every piece of data.
• Based on this training data, the algorithm has to generalize
such that it is able to correctly (or with a low margin of error)
respond to all possible inputs.
• In essence: The algorithm should produce sensible outputs for
inputs that weren't encountered during training.
• Also called learning from exemplars

7. Features
Vectors
Features
vector
fig.1:- Flowchart of unsupervised learning
Training
text,
document
, images,
sounds…
Labels
New text
document,
Image , sound
Predictive
Modeling
Expected
Lebel
MACHINE
LEARNING
ALGORITHM

8. Classification Problems
Output is a discrete variable
Supervised Learning
Regression problems
Output is continuous

9. Unsupervised Learning
• Conceptually Different Problem.
• No information about correct outputs are available.
• No Regression No guesses about the function can be made
• In essence: The aim of unsupervised learning is to find clusters of
similar inputs in the data without being explicitly told that some
datapoints belong to one class and the other in other classes.
• The algorithm has to discover this similarity by itself .

10. Features
vectors
features
vector
fig.2:- Flowchart of unsupervised learning
Training
text,
document
, images,
sounds…
Labels
New text
document,
Image , sound
Predictive
Modeling
Likelihood
Or cluster id
Or better
representation
MACHINE
LEARNING
ALGORITHM

11. Unsupervised Learning: Clustering
• Clustering is considered to be the most important unsupervised
learning problem.
• Deals with finding structure in unlabeled data i.e. unlike supervised
learning, target data isn't provided.
• In essence: Clustering is “the process of organizing objects into
groups whose members are similar in some way”.

12. Reinforcement Learning:
• Stands in the middle ground between supervised and unsupervised
learning.
• The algorithm is provided information about whether or not the
answer is correct but not how to improve it.
• The reinforcement learner has to try out different strategies and see
which works best.
• In essence: The algorithm searches over the state space of possible
inputs and outputs in order to maximize a reward

13. fig.3:- Flowchart of reinforcement learning
Performance
Learning
Environment Knowledge

14. Steps to solve a Machine Learning problem
Data processing
Clean data to
have
homogeneity
Feature
Engineering
Making your data
more useful
Algorithm section
& Training
selecting the right
machine learning
model
Making
predictions
evaluate the
model
Data gathering
Collect data from
various sources

15. Applications of Machine Learning
Face Recognition automatically determines if two faces are likely
to correspond to the same person.
Speech Recognition is invading our lives. It’s built into
our phones, our game consoles and our smart watches.
It’s even automating our homes.
With fully Self-Driving Technology, you’ll be able to get
where you want to go at the push of a button without the
need for a person at the wheel.

16. Growth of Machine Learning
• Machine learning is preferred approach to
• Speech recognition, Natural language processing
• Computer vision
• Medical outcomes analysis
• Robot control
• Computational biology
• This trend is accelerating
• Improved machine learning algorithms
• Improved data capture, networking, faster computers
• Software too complex to write by hand
• New sensors / IO devices
• Demand for self-customization to user, environment
• It turns out to be difficult to extract knowledge from human experts  failure of
expert systems in the 1980’s.

17. Future scope
• The scope of Machine Learning is not limited to the investment
sector. Rather, it is expanding across all fields such as banking
and finance, information technology, media & entertainment,
gaming, and the automotive industry.
• Robotics
• Quantum Computing
• Computer Vision

18. Conclusion
• As we move forward into the digital age, our technology continues to
make leaps and strides forward.
• This incredible form of artificial intelligence is already being used in
various industries and professions. From marketing, to medicine, and
web security.
• This technology can improve our lives in several numerous ways.

20. References
• Internshala online Training
• IEEE Transactions on Neural Networks
• IEEE Transactions on Pattern Analysis and Machine Intelligence