![Lesson: 1
What is Machine Learning?
(Layman’s term)
[what is Machine Learning.
In this lesson, we will try to understand machine learning from a Layman’s term.]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-1-320.jpg)
![[ But, he is a human being. He can observe
and learn ]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-7-320.jpg)
![12
Machines follow instructions
What about a Machine ?
[ It can not take decision of its own]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-12-320.jpg)
![14
Machines follow instructions
What about a Machine ?
• Comparison
• Print
• Plotting a chart
[ But, we can ask a machine to make a decision of its own ]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-14-320.jpg)
![15
What is Machine Learning?
[ We want a machine to act like a human]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-15-320.jpg)
![16
What is Machine Learning?
[ to identify this object.]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-16-320.jpg)
![17
What is Machine Learning?
[ predict the price in future]
Price in 2025?](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-17-320.jpg)
![18
What is Machine Learning?
[ Natural Language understand, and correct grammar ]
I made met him yesterday](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-18-320.jpg)
![19
What is Machine Learning?
recognize face
[ Recognize Faces ]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-19-320.jpg)
![20
What is Machine Learning?
[ What do we do?
Just like, what we did to human,
we need to provide experience
to the machine.
]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-20-320.jpg)
![21
What is Machine Learning?
Dataset
[
This what we called as Data
or Training dataset
So, we first need to provide
training dataset to the
machine
]
+](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-21-320.jpg)
![22
What is Machine Learning?
Dataset
+
[ Then, devise algorithms and execute programs on the
data
With respect to the underlying target tasks ]
+](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-22-320.jpg)
![23
What is Machine Learning?
Dataset
+
[ Then, using the programs, Identify
required rules ]
+ +](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-23-320.jpg)
![24
What is Machine Learning?
Dataset
+
[extract required patterns ]
+ +](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-24-320.jpg)
![25
What is Machine Learning?
Dataset
+
[ Identify relations ]
+ +](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-25-320.jpg)
![26
What is Machine Learning?
Dataset
+
[ So that machine can derive inferences
from the data ]
+ + =](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-26-320.jpg)
![28
Machine Learning Paradigms
• Supervised
• Unsupervised Learning
• Reinforcement learning
[ We as human being solve various types of problem in our day-to-day life, <pause> Various
decisions need to be taken.
Depending on the nature of the problem, machine learning tasks can be broadly divided in ]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-28-320.jpg)
![29
What is Supervised Learning?
[In supervised learning, we need some thing called a Labelled Training Dataset ]
CAR
CAR
BIKE
BIKE
Samples
+
Labels
= Training Dataset](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-29-320.jpg)
![30
What is Supervised Learning?
[ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and
produces an output value.]
CAR
CAR
BIKE
BIKE
Samples
+
Labels
= Training Dataset =](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-30-320.jpg)
![31
What is Supervised Learning?
[ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and
produces an output value.]
CAR
CAR
BIKE
BIKE
Samples
+
Labels
= Training Dataset =](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-31-320.jpg)
![32
What is Supervised Learning?
[ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and
produces an output value.]
CAR
CAR
BIKE
BIKE
Samples
+
Labels
= Training Dataset = CAR](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-32-320.jpg)
![34
What is Supervised Learning?
[ Predefined classes means, it will produce output only from the labels defined in the dataset. For example,
even if we input a bus, it will produce either CAR or BIKE ]
CAR
CAR
BIKE
BIKE
Samples
+
Labels
= Training Dataset = CAR
Classification](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-34-320.jpg)
![37
[
The classification and Regression problems are supervised, because the decision depends on the
characteristics of the ground truth labels or values present in the dataset, which we define as experience
]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-37-320.jpg)
![38
What is Unsupervised Learning
Dataset
[ In the unsupervised learning, we do not need to know the labels or Ground truth values ]
CAR
CAR
BIKE
BIKE](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-38-320.jpg)
![39
What is Unsupervised Learning
Dataset
[ The task is to identify the patterns like group the similar objects together ]
Clustering](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-39-320.jpg)
![40
What is Unsupervised Learning
Dataset
[ Association rules like ]
Association Rules Mining](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-40-320.jpg)
![44
What is Reinforcement Learning
[ It is also known as learning from trials and errors ]](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-44-320.jpg)
![Summary
[ In this lesion, we have learnt ]
what is machine learning
what are the machine learning paradigms](https://image.slidesharecdn.com/lesson1-250214082719-2fe4f67d/85/Machine-learning-for-beginners-A-simple-approach-52-320.jpg)
Machine learning for beginners. A simple approach
- 1. Lesson: 1 What is Machine Learning? (Layman’s term) [what is Machine Learning. In this lesson, we will try to understand machine learning from a Layman’s term.]
- 2. 2 Human can learn from past experience and make decision of its own
- 3. 3 What is this object?
- 4. 4 What is this object? CAR CAR BIKE BIKE It is a CAR
- 5. 5 Let us ask the same question to him What is this object?
- 6. 6 Let us ask the same question to him What is this object? ?
- 7. [ But, he is a human being. He can observe and learn ]
- 8. 8 Let us make him learn show him
- 9. 9 Let us make him learn show him CAR CAR BIKE BIKE
- 10. 10 Let us ask the same question now What is this object? CAR CAR BIKE BIKE Past experience
- 11. 11 Let us ask the same question now What is this object? CAR CAR CAR BIKE BIKE
- 12. 12 Machines follow instructions What about a Machine ? [ It can not take decision of its own]
- 13. 13 Machines follow instructions What about a Machine ? We can ask a machine • To perform an arithmetic operations such as • Addition • Multiplication • Division
- 14. 14 Machines follow instructions What about a Machine ? • Comparison • Print • Plotting a chart [ But, we can ask a machine to make a decision of its own ]
- 15. 15 What is Machine Learning? [ We want a machine to act like a human]
- 16. 16 What is Machine Learning? [ to identify this object.]
- 17. 17 What is Machine Learning? [ predict the price in future] Price in 2025?
- 18. 18 What is Machine Learning? [ Natural Language understand, and correct grammar ] I made met him yesterday
- 19. 19 What is Machine Learning? recognize face [ Recognize Faces ]
- 20. 20 What is Machine Learning? [ What do we do? Just like, what we did to human, we need to provide experience to the machine. ]
- 21. 21 What is Machine Learning? Dataset [ This what we called as Data or Training dataset So, we first need to provide training dataset to the machine ] +
- 22. 22 What is Machine Learning? Dataset + [ Then, devise algorithms and execute programs on the data With respect to the underlying target tasks ] +
- 23. 23 What is Machine Learning? Dataset + [ Then, using the programs, Identify required rules ] + +
- 24. 24 What is Machine Learning? Dataset + [extract required patterns ] + +
- 25. 25 What is Machine Learning? Dataset + [ Identify relations ] + +
- 26. 26 What is Machine Learning? Dataset + [ So that machine can derive inferences from the data ] + + =
- 27. 27 In summary, what is machine learning? Given a machine learning problem • Identify and create the appropriate dataset • Perform computation to learn • Required rules, pattern and relations • Output the decision
- 28. 28 Machine Learning Paradigms • Supervised • Unsupervised Learning • Reinforcement learning [ We as human being solve various types of problem in our day-to-day life, <pause> Various decisions need to be taken. Depending on the nature of the problem, machine learning tasks can be broadly divided in ]
- 29. 29 What is Supervised Learning? [In supervised learning, we need some thing called a Labelled Training Dataset ] CAR CAR BIKE BIKE Samples + Labels = Training Dataset
- 30. 30 What is Supervised Learning? [ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and produces an output value.] CAR CAR BIKE BIKE Samples + Labels = Training Dataset =
- 31. 31 What is Supervised Learning? [ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and produces an output value.] CAR CAR BIKE BIKE Samples + Labels = Training Dataset =
- 32. 32 What is Supervised Learning? [ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and produces an output value.] CAR CAR BIKE BIKE Samples + Labels = Training Dataset = CAR
- 33. 33 What is Supervised Learning? [ If the possible output values of the function are predefined and discrete/categorical, it is called Classification CAR CAR BIKE BIKE Samples + Labels = Training Dataset = CAR Classification
- 34. 34 What is Supervised Learning? [ Predefined classes means, it will produce output only from the labels defined in the dataset. For example, even if we input a bus, it will produce either CAR or BIKE ] CAR CAR BIKE BIKE Samples + Labels = Training Dataset = CAR Classification
- 35. 35 Classifier Elephant Tiger Dataset Identify the Animal ? Classifier Elephant
- 36. 36 Regression Dataset [ If the possible output values of the function are continuous real values, then it is called Regression = 20500.50 Regression
- 37. 37 [ The classification and Regression problems are supervised, because the decision depends on the characteristics of the ground truth labels or values present in the dataset, which we define as experience ]
- 38. 38 What is Unsupervised Learning Dataset [ In the unsupervised learning, we do not need to know the labels or Ground truth values ] CAR CAR BIKE BIKE
- 39. 39 What is Unsupervised Learning Dataset [ The task is to identify the patterns like group the similar objects together ] Clustering
- 40. 40 What is Unsupervised Learning Dataset [ Association rules like ] Association Rules Mining
- 41. 41 More Example Unsupervised Learning Dataset
- 42. 42 More Example Unsupervised Learning Dataset
- 43. 43 More Example Unsupervised Learning
- 44. 44 What is Reinforcement Learning [ It is also known as learning from trials and errors ]
- 45. 45 What is Reinforcement Learning
- 46. 46 What is Reinforcement Learning
- 47. 47 What is Reinforcement Learning
- 48. 48 Another Example Agent Task Environment
- 51. 51 Reinforcement Learning Reward Baby Learn from the Trials and Errors Reinforcement Learning
- 52. Summary [ In this lesion, we have learnt ] what is machine learning what are the machine learning paradigms