2. What is Machine Learning?
O Machine learning is an application of
artificial intelligence that involves algorithms
and data that automatically analyse and
make decision by itself without human
intervention.
O It describes how computer perform tasks on
their own by previous experiences.
O Therefore we can say in machine language
artificial intelligence is generated on the
basis of experience.
30-07-2022
Sayak Maity
3. Normal Computer vs ML
O The difference between normal computer
software and machine learning is that a
human developer hasn’t given codes that
instructs the system how to react to
situation, instead it is being trained by a
large number of data.
30-07-2022
Sayak Maity
4. 30-07-2022
Sayak Maity
Some of the machine learning algorithms
are:
• Neural Networks
• Random Forests
• Decision trees
• Genetic algorithm
• Radial basis function
• Sigmoid
5. Types of Machine Learning
There are three types of machine learning
O Supervised learning
O Unsupervised learning
O Reinforcement learning
30-07-2022
Sayak Maity
6. Machine Learning Uses:
O Traffic prediction
O Virtual Personal Assistant
O Speech recognition
O Email spam and malware filtering
O Bioinformatics
O Natural language processing
30-07-2022
Sayak Maity
7. Real Time Examples for ML
O TRAFFIC PREDICTION
O VIRTUAL PERSONAL ASSISTANT
O ONLINE TRANSPORTATION
O SOCIAL MEDIA SERVICES
O EMAIL SPAM FILTERING
O PRODUCT RECOMMENDATION
O ONLINE FRAUD DETECTION
30-07-2022
Sayak Maity
9. Difference Between Machine
Learning And Artificial
Intelligence
O Artificial Intelligence is a concept of creating
intelligent machines that stimulates human
behaviour whereas Machine learning is a
subset of Artificial intelligence that allows
machine to learn from data without being
programmed.
30-07-2022
Sayak Maity
10. Advantages of Machine
Learning
O Fast, Accurate, Efficient.
O Automation of most applications.
O Wide range of real life applications.
O Enhanced cyber security and spam
detection.
O No human Intervention is needed.
O Handling multi dimensional data.
30-07-2022
Sayak Maity
11. Disadvantages of Machine
Learning
O It is very difficult to identify and rectify the
errors.
O Data Acquisition.
O Interpretation of results Requires more time
and space.
30-07-2022
Sayak Maity
12. Reinforcement learning
30-07-2022
Sayak Maity
Reinforcement learning is an area of Machine
Learning.
It is about taking suitable action to maximize reward in
a particular situation . It is employed by various
software and machines to find the best possible
behavior or path it should take in a specific situation.
13. Types of Reinforcement
O There are two types of Reinforcement:
O Positive –
Positive Reinforcement is defined as when an event,
occurs due to a particular behavior, increases the
strength and the frequency of the behavior.
O Negative –
Negative Reinforcement is defined as strengthening
of behavior because a negative condition is stopped
or avoided.
30-07-2022
Sayak Maity
14. Applications of Reinforced Learning
O Various Practical applications of Reinforcement
Learning –
O RL can be used in robotics for industrial
automation.
O RL can be used in machine learning and data
processing
O RL can be used to create training systems that
provide custom instruction and materials
according to the requirement of students.
30-07-2022
Sayak Maity
