1
00:00:00,000 --> 00:00:01,976
[MUSIC PLAYING]

2
00:00:01,976 --> 00:00:18,280


3
00:00:18,280 --> 00:00:19,280
SPEAKER 1: Hello, world.

4
00:00:19,280 --> 00:00:20,650
This is CS50.

5
00:00:20,650 --> 00:00:23,200
And this is an Introduction
to Artificial Intelligence

6
00:00:23,200 --> 00:00:26,080
with Python with CS50's own Brian Yu.

7
00:00:26,080 --> 00:00:30,160
This course picks up where CS50 itself
leaves off and explores the concepts

8
00:00:30,160 --> 00:00:33,108
and algorithms at the
foundation of modern AI.

9
00:00:33,108 --> 00:00:34,900
BRIAN YU: We'll start
with a look at how AI

10
00:00:34,900 --> 00:00:37,945
can search for solutions to
problems, whether those problems are

11
00:00:37,945 --> 00:00:39,820
learning how to play a
game or trying to find

12
00:00:39,820 --> 00:00:41,890
driving directions to a destination.

13
00:00:41,890 --> 00:00:44,620
We'll then look at how AI
can represent information--

14
00:00:44,620 --> 00:00:46,630
both knowledge that our
AI is certain about,

15
00:00:46,630 --> 00:00:50,238
but also information and events about
which our AI might be uncertain.

16
00:00:50,238 --> 00:00:52,030
Learning how to represent
that information,

17
00:00:52,030 --> 00:00:54,430
but more importantly, how to
use that information to draw

18
00:00:54,430 --> 00:00:57,100
inferences and new conclusions as well.

19
00:00:57,100 --> 00:01:00,820
We'll explore how I can solve various
types of optimization problems-- trying

20
00:01:00,820 --> 00:01:05,260
to maximize profits or minimize cost
or satisfy some other constraints--

21
00:01:05,260 --> 00:01:08,710
before turning our attention to the
fast-growing field of machine learning,

22
00:01:08,710 --> 00:01:11,510
where we won't tell our AI
exactly how to solve a problem.

23
00:01:11,510 --> 00:01:14,920
But instead, give our AI
access to data and experiences

24
00:01:14,920 --> 00:01:18,790
so that our AI can learn on its
own how to perform these tasks.

25
00:01:18,790 --> 00:01:20,920
In particular, we'll look
at neural networks, one

26
00:01:20,920 --> 00:01:24,310
of the most popular tools in modern
machine learning, inspired by the way

27
00:01:24,310 --> 00:01:26,620
that human brains learn
and reason as well.

28
00:01:26,620 --> 00:01:30,060
Before finally taking a look at the
world of natural language processing,

29
00:01:30,060 --> 00:01:33,670
so that it's not just us humans learning
to learn how artificial intelligence is

30
00:01:33,670 --> 00:01:37,210
able to speak, but also AI learning
how to understand and interpret

31
00:01:37,210 --> 00:01:38,740
human language as well.

32
00:01:38,740 --> 00:01:41,690
We'll explore these ideas and
algorithms and, along the way,

33
00:01:41,690 --> 00:01:44,320
give you the opportunity to
build your own AI programs

34
00:01:44,320 --> 00:01:46,300
to implement all of this and more.

35
00:01:46,300 --> 00:01:48,760
This is CS50.

36
00:01:48,760 --> 00:01:52,000