1

2
3
4
5
6
7
8
9
With the right data and the right model,
machine learning can solve many problems.

But finding the right

data and training the
right model
can be difficult.
10
AI

ML

Deep
Learning 11
Car photo © Google; kitten photo © source unknown. All rights reserved.
This content is excluded from our Creative Commons license. For more information, 12
see https://ocw.mit.edu/help/faq-fair-use/.
 AI can be general or narrow.

Terminator image © Skydance Media; car photo © Google. All rights reserved.
This content is excluded from our Creative Commons license. For more 13
information, see https://ocw.mit.edu/help/faq-fair-use/.
 AI can be general or narrow.

Terminator image © Skydance Media. All rights reserved.

This content is excluded from our Creative Commons license. For more 14
information, see https://ocw.mit.edu/help/faq-fair-use/.
 AI can be general or narrow.

Terminator image © Skydance Media; car photo © Google. All rights reserved.
This content is excluded from our Creative Commons license. For more 15
information, see https://ocw.mit.edu/help/faq-fair-use/.
 AI can be general or narrow.

© source unknown. All rights reserved. This content is excluded from our Creative Commons license. 16
For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 AI can be general or narrow.

Terminator image © Skydance Media; car photo © Google. All rights reserved.
This content is excluded from our Creative Commons license. For more 17
information, see https://ocw.mit.edu/help/faq-fair-use/.
 Typical “narrow” tasks include vision,
language processing, and planning.

Photo of eye © source unknown; smart speaker and map detail © Google. All rights reserved. This content is excluded
18
from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 Typical “narrow” tasks include vision,
language processing, and planning.

Photo of eye © source unknown. All rights reserved. This content is excluded from our 19
Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 Typical “narrow” tasks include vision,
language processing, and planning.

Photo © Google. All rights reserved. This content is excluded from our Creative Commons license. 20
For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 Typical “narrow” tasks include vision,
language processing, and planning.

© Google. All rights reserved. This content is excluded from our Creative Commons license. 21
For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 Typical “narrow” tasks include vision,
language processing, and planning.

Photo of eye © source unknown; smart speaker and map detail © Google. All rights reserved. This content is excluded
from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/. 22
There are many ways to build AI,
including expert systems and tree search.

23
There are many ways to build AI,
including expert systems and tree search.

24
There are many ways to build AI,
including expert systems and tree search.

25
There are many ways to build AI,
including expert systems and tree search.

26
AI

ML

27
 Machine learning can perform many tasks,
i.e. classification, clustering, and regression.

Cat photo © source unknown. All rights reserved. This content is excluded from our Creative 28
Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 Machine learning can perform many tasks,
i.e. classification, clustering, and regression.

© source unknown. All rights reserved. This content is excluded from our Creative 29
Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.
Machine learning can perform many tasks,
i.e. classification, clustering, and regression.

30
Machine learning can perform many tasks,
i.e. classification, clustering, and regression.

31
 Machine learning can perform many tasks,
i.e. classification, clustering, and regression.

Cat photo © source unknown. All rights reserved. This content is excluded from our Creative
Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/. 32
 There are three types of learning:
supervised, unsupervised, and
reinforcement learning.

Images © source unknown. All rights reserved. This content is excluded from our Creative
Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/. 33
 There are three types of learning:
supervised, unsupervised, and
reinforcement learning.

Images © source unknown. All rights reserved. This content is excluded from our Creative 34
Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 There are three types of learning:
supervised, unsupervised, and
reinforcement learning.

Photo © source unknown. All rights reserved. This content is excluded from our Creative 35
Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 There are three types of learning:
supervised, unsupervised, and
reinforcement learning.

Images © source unknown. All rights reserved. This content is excluded from our Creative
36
Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 There are three types of learning:
supervised, unsupervised, and
reinforcement learning.

Images © source unknown. All rights reserved. This content is excluded from our Creative 37
Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.
AI

ML

Deep
Learning 38
With the right data and the right model,
machine learning can solve many problems.

But finding the right

data and training the
right model
can be difficult.
39
 1. Define a problem.

Cat photo © source unknown; dog photo © Getty images. All rights reserved. This content is excluded from our
40
Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.
Golden retriever photo © Getty Images; other photos © source unknown. All rights reserved. This content
is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.

2. Find data.

Cat
Dog
Cat

Cat Do g Dog
41
Golden retriever photo © Getty Images; other photos © source unknown. All rights reserved. This content
is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.

3. Clean data.

Cat
Dog
Cat

Cat Do g Dog
42
Golden retriever photo © Getty Images; other photos © source unknown. All rights reserved. This content
is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.

3. Clean data.

Dog Cat
Cat

Cat Dog Dog

43
4. Choose a model.
Dog Cats
s
Always Always

Sometimes Sometimes

44
5. Train the model.

45
 5. Train the model.

Cat

© source unknown. All rights reserved. This content is excluded from our Creative Commons license.
46
For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 5. Train the model.

Cat

© source unknown. All rights reserved. This content is excluded from our Creative Commons license. 47
For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 5. Train the model.

Dog

© source unknown. All rights reserved. This content is excluded from our Creative Commons license.
48
For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 5. Train the model.

Dog

© source unknown. All rights reserved. This content is excluded from our Creative Commons license. 49
For more information, see https://ocw.mit.edu/help/faq-fair-use/.
 6. Test the model.

Cat

© source unknown. All rights reserved. This content is excluded from our Creative Commons license.
50
For more information, see https://ocw.mit.edu/help/faq-fair-use/.
7. Deploy the model.

 51
Golden retriever photo © Getty Images; other photos © source unknown. All rights reserved. This content
52
is excluded from our Creative Commons license. For more information, see https://ocw.mit.edu/help/faq-fair-use/.
AI

ML

Deep
Learning 53
1.Goal?

54
1.Goal?
2.Training data?

55
1.Goal?
2.Training data?
3.Model?

56
1.Goal?
2.Training data?
3.Model?
4.Accuracy?
57
1.Goal?
2.Training data?
3.Model?
4.Accuracy?
58
AI 101
By Brandon Leshchinskiy

59
1.Goal?
2.Training data?
3.Model?
4.Accuracy?
60
MIT OpenCourseWare

https://ocw.mit.edu/

RES.6-013 AI 101 Fall 2021

For information about citing these materials or our Terms of Use, visit: https://ocw.mit.edu/terms.

61