シャドーイング練習: P2 什么是机器学习【2024公认最好的 | 吴恩达机器学习 | 教程 | Machine Learning Specialization(超爽中英!)】 - 動画で英語スピーキングを学ぶ
レッスンを作成中...
1
So what is machine learning?
2
In this video you learn a definition of what it is
3
and also get a sense of when you might want to apply it.
4
Let's take a look together.
5
Here's the definition of what is machine learning that is attributed to Arthur Samuel.
6
He defined machine learning as the field of study that gives computers the ability to learn without being explicitly programmed.
7
Salva's claim to fame was that back in the 1950s he wrote a checkers playing program.
8
And the amazing thing about this program was that Arthur Samuel himself wasn't a very good checkers player.
9
What he did was he had programmed a computer to play maybe tens of thousands of games against himself.
10
And by watching what sorts of board positions tended to lead to wins and what positions tended to lead to losses,
11
the checkers playing program learned over time what are good or bad board positions.
12
By trying to get to good and avoid bad positions, his program learned to get better and better at playing checkers.
13
Because the computer had the patience to play tens of thousands of games against itself,
14
it was able to get so much checkers playing experience that eventually it became a better checkers player than author Samuel himself.
15
Now, throughout these videos, besides me trying to talk about stuff,
16
I'll occasionally ask you a question to help make sure you understand the content here's one about what happens
17
if the computer had played far fewer games please take a look
18
and pick whichever you think is a better answer thanks for looking at the quiz and so
19
if you had selected this answer would have made it worse
20
then you got it right in general the more opportunities you give a learning algorithm to learn, the better it will perform.
21
If you didn't select the correct answer the first time, that's totally okay too.
22
The point of these quiz questions isn't to see if you can get them all correct on the first try.
23
These questions are here just to help you practice the concepts you're learning.
24
Author Samuel's definition was a rather informal one, but in the next two videos, we'll dive deeper together into what are the major types types of machine learning algorithms.
25
In this class, you learn about many different learning algorithms.
26
The two main types of machine learning are supervised learning and unsupervised learning.
27
We'll define what these terms mean more in the next couple videos.
28
Of these two, supervised learning is the type of machine learning that is used most in many real -world applications,
29
and that has seen the most rapid advancement and innovation.
30
In this specialization, which has three causes in total, the first and second causes will focus on supervised learning,
31
and the third will focus on unsupervised learning.
32
You might have also heard of reinforcement learning.
33
This is another type of machine learning algorithm that I'll talk about briefly,
34
but by far the two most used types of learning algorithms today are supervised learning and unsupervised learning.
35
That's why we'll spend most of this class talking about them.
36
The other thing we're going to spend a lot of time on in this specialization is practical advice for applying learning algorithms.
37
This is something I feel pretty strongly about.
38
Teaching about learning algorithms is like giving someone a set of tools
39
and equally important
40
or even more importance than making sure you have great tools is making sure you know how to apply them
41
because you know what good is it
42
if someone were to give you a state -of -the -art hammer
43
or a state -of -the -art hand drill
44
and say good luck now you have all the tools you
45
need to build a three -story house It doesn't really work like that.
46
And so too in machine learning, making sure you have the tools is really important.
47
And so it's making sure that you know how to apply the tools of machine learning effectively.
48
So that's what you get in this class, the tools as well as the skills in applying them effectively.
49
I regularly visit with friends and teams in some of the top tech companies.
50
And even today, I see experienced machine learning teams apply machine learning algorithms to some problems.
51
And sometimes they've been going at it for six months without much success.
52
And when I look at what they're doing, I sometimes feel like I could have told them six months ago that the current approach won't work.
53
And there's a different way of using these tools that will give them a much better chance of success.
54
So in this class, one of the relatively unique things you learn is you learn
55
a lot about the best practices for how to actually develop a practical, valuable machine learning system.
56
This way, you're less likely to end up in one of those teams
57
that end up losing six months going in the wrong direction.
58
In this class, you gain a sense of how the most skilled machine learning engineers build systems,
59
and I hope you finish this class as one of those very rare people in today's world
60
that know how to design and build serious machine learning systems.
61
So that's machine learning.
62
In the next video, let's look more deeply at what is supervised learning and also what is unsupervised learning.
63
In addition, you learn when you might want to use each of them, supervised and unsupervised learning.
64
I'll see you in the next video.
📺 同じチャンネル
✨ おすすめ動画
C12
175 文
What is a PLC and how does it work?
Business EnglishUniversity StudentsWorking Adults
C12
169 文
What Is Jev? The AI Model That Doesn't Generate Text
Business EnglishUniversity StudentsWorking Adults
C11
245 文
QA Automation Interview Questions and Answers
Business EnglishInterview EnglishUniversity Students
B2131 文
what chess does to your brain
Business EnglishUniversity StudentsWorking Adults
C12
764 文
11. Introduction to Machine Learning
Business EnglishUniversity StudentsWorking Adults
C11
177 文
AWS Machine Learning Engineer Associate: What You Need to Know
Business EnglishUniversity StudentsWorking Adults
C11
74 文
LangChain in 5 Minutes (Explained Clearly)
Business EnglishUniversity StudentsWorking Adults
C11
253 文
AI biết code, vì sao vẫn phải học lập trình? | đi-code ep 35
Business EnglishUniversity StudentsWorking Adults
C12
182 文
We Let $200 GPT-Pro Think for 7 Days on Unsolved Math
Business EnglishUniversity StudentsWorking Adults
C12
190 文
Supervised Learning: Crash Course AI #2
Business EnglishUniversity StudentsWorking Adults
C18
114 文
AI, Machine Learning, Deep Learning and Generative AI Explained
Business EnglishUniversity StudentsWorking Adults
このレッスンの語彙とスピーキングのポイント
この動画には、シャドーイング用の文が64文、単語が927語あります。 音声の長さは5:36です。 話す速さは1分あたり約166語で、日常会話に近い自然なペースです。 単語の88%は英語の頻出3,000語に含まれます。残りは練習の前に確認しておきましょう。
この動画の重要語彙
動画に出てくる覚えておきたい単語15語を、発音と意味つきで紹介します。
| 単語 | 発音 | 意味 |
|---|---|---|
| algorithm 名詞 | /ˈælɡəɹɪðm̩/ | アルゴリズム, 演算手順 |
| practical 形容詞 | /ˈpɹæk.tɪ.kəl/ | 実践的な |
| select 動詞 | /sɪˈlɛkt/ | 選ぶ |
| skill 名詞 | /skɪl/ | 腕, 技 |
| quiz 名詞 | /kwɪz/ | クイズ |
| deeply 副詞 | /ˈdi(ː)pli/ | 深く |
| equally 副詞 | /ˈiːkwəli/ | 等しく, 平等に |
| occasionally 副詞 | /əˈkeɪʒənəli/ | たまに, 偶に |
| rapid 形容詞 | /ˈɹæp.ɪd/ | 速い, 急な |
| fame 名詞 | /feɪm/ | 有名 |
| innovation 名詞 | /ˌɪn.əˈveɪ.ʃən/ | イノベーション, 革新 |
| patience 名詞 | /ˈpeɪ̯.ʃəns/ | 辛抱, 忍耐 |
| hammer 名詞 | /ˈhæmɚ/ | 金槌, 槌 |
| dive 動詞 | /daɪv/ | 潜る |
| drill 名詞 | /dɹɪl/ | ドリル |
注意したい発音
話し手はI'll, we'll, you'reなど、短縮形や弱形を16回使っています。聞こえたとおりの短い形で発音しましょう。
- 「sh」と「zh」の音: occasionally /əˈkeɪʒənəli/, innovation /ˌɪn.əˈveɪ.ʃən/, patience /ˈpeɪ̯.ʃəns/, specialization [ˌspɛʃəlaɪ̯ˈzeɪ̯ʃn̩]
- 長い単語（アクセントの位置に注意）: occasionally /əˈkeɪʒənəli/, innovation /ˌɪn.əˈveɪ.ʃən/, specialization [ˌspɛʃəlaɪ̯ˈzeɪ̯ʃn̩], reinforcement /ˌɹiːɪnˈfɔːsmənt/
この動画での練習方法
- まず声を出さずに動画を最後まで聞き、知らない単語をメモします。
- まず0.75倍速で一文ずつシャドーイングし、慣れてきたら通常の速度に戻します。
- 自分の声を録音して元の音声と比べます。algorithm, practical, selectなどの単語に特に注意しましょう。
シャドーイングとは？英語上達に効果的な理由
シャドーイング（Shadowing）は、もともとプロの通訳者養成プログラムで開発された言語学習法で、多言語習得者として知られるDr. Alexander Arguelles によって広く普及されました。方法はシンプルですが非常に効果的：ネイティブスピーカーの英語を聞きながら、1〜2秒の遅延で声に出してすぐに繰り返す——まるで「影（shadow）」のように話者を追いかけます。文法ドリルや受動的なリスニングと異なり、シャドーイングは脳と口の筋肉が同時にリアルタイムで英語を処理・再現することを強制します。研究により、発音精度、抑揚、リズム、連音、リスニング力、そして会話の流暢さが大幅に向上することが確認されています。IELTSスピーキング対策や自然な英語コミュニケーションを目指す方に特におすすめです。