Prática de Shadowing: Ridge vs Lasso Regression, Visualized!!! - Aprenda a falar inglês com vídeo
Escolha um modo de prática
Cada modo abre uma sala de prática em tela cheia.
86 frases
Se as frases estiverem muito curtas ou longas, clique em Edit para ajustá-las.
1
Ridge, regression versus lasso regression, which one will survive?
2
StatQuest.
3
Hello, I'm Josh Starmer and welcome to StatQuest.
4
Today we're going to talk about ridge versus lasso regression and the differences are going to be visualized.
5
Note, this StatQuest assumes that you are already familiar with ridge and lasso regression.
6
If not, check out the quests.
7
To show you the difference between ridge and lasso regression, we're going to use a very simple data set that consists of weight and height measurements.
8
And we'll start by fitting this horizontal line to the data.
9
This horizontal line represents a terrible fit.
10
And we can measure how bad that fit is by calculating residuals, the difference between the observed and predicted values.
11
In order to compare the horizontal line to other lines fit to the data, we will plot the sum of the squared residuals on a graph.
12
The y-axis on this graph is the sum of the squared residuals,
13
and the x-axis represents different slope values for the fitted line.
14
In this case, the slope for the horizontal line is 0.
15
Now let's increase the slope to 0.2, and calculate a new value for the sum of the squared residuals.
16
Now let's increase the slope to 0.4, and calculate a new value for the sum of the squared residuals.
17
We can keep plugging in new values for the slope and plotting the sum of the squared residuals,
18
Or we can just plot the curve for this equation.
19
We can see that the best fitting line is at the bottom of the parabola.
20
In other words, when the slope equals 0.45, we get the lowest sum of the squared residuals.
21
In this example, we simply calculated the sum of the squared residuals for different slopes.
22
Now let's add the ridge regression penalty, aka the L2 norm.
23
if you asked me, it should be called the squared penalty, since that's what it is, and, for me, way easier to remember.
24
The thick blue line that we just drew represents lambda equals zero.
25
This is because when lambda equals zero, the penalty is equal to zero,
26
regardless of the slope, and we are left with the original sum of squared residuals.
27
Now let's see what happens when we set lambda equal to 10.
28
And just like before, we'll start with a horizontal line, only this time, the line is orange.
29
Just like before, we can calculate the residuals.
30
And we can calculate the sum of the squared residuals plus lambda times the slope squared.
31
In this case, lambda equals 10.
32
And the slope of the horizontal line is 0.
33
So the penalty is 0.
34
So we plot the sum of the squared residuals here.
35
Now let's increase the slope to 0.2.
36
Note, the residuals are smaller than before, so the sum of squared residuals is smaller than before.
37
But now the penalty is 0.4.
38
And that gives us this point on the graph.
39
Now let's increase the slope to 0.4.
40
And the residuals are even smaller.
41
But now the penalty is 1.6.
42
And that gives us this point on the graph.
43
And like we did before, we can keep plugging in new values for the slope and plotting the sum of the squared residuals plus the penalty,
44
or we can just plot the curve with a thick orange line that represents lambda equals 10.
45
The bottom of the parabola is where the slope gives us the lowest sum of squared residuals plus penalty,
46
and that corresponds to this specific line.
47
And when we compare that to the optimal slope when lambda equals zero,
48
we see that setting lambda equal to 10 results in a smaller optimal slope.
49
Note, we can also see that when lambda equals 10, the lowest point in the parabola is closer to zero than when lambda equals zero.
50
So, either way we look at it, we see that the larger value for lambda shrunk the optimal value for the slope.
51
Likewise, the thick green line represents lambda equals 20.
52
We see that the minimum value is closer to zero, and the optimal slope has shrunk some more.
53
The purple lines represent lambda equals 40, and it shrinks the slope even more.
54
In other words, as we increase lambda for the ridge regression penalty, a.k.a the L2 penalty, a.k.a the square penalty,
55
The optimal slope gets closer and closer to zero, but it does not equal zero.
56
Bam!
57
Now let's see what happens if we use the lasso penalty, a.k.a the L1 norm, or, if you asked me,
58
I'd call it the absolute value penalty.
59
Unfortunately, no one asked me.
60
Again, the thick blue line represents lambda equals zero, so there is no extra penalty.
61
This is because when we plug lambda equals zero into the equation, the penalty becomes zero.
62
And we are left with the original sum of the squared residuals.
63
Note, just like before, we'll keep track of the best fitting line plus penalty in this graph on the left.
64
The thick orange line represents lambda equals 10, so now we are turning on the penalty and shrinking the slope.
65
When lambda equals 10, we start to see a kink in the curve where the slope is 0.
66
The thick green line represents lambda equals 20, and this kink at zero is becoming more prominent.
67
Lastly, the thick purple line represents lambda equals 40.
68
And now the kink at zero is super obvious.
69
Now the lowest point in the purple curve,
70
aka the optimal slope given the absolute value penalty when lambda equals 40, is zero.
71
And that means the slope of the optimal line is 0.
72
And that means when lambda equals 40, we ignore weight as a variable when predicting height.
73
Double bam!
74
In summary, when we increase the ridge regression penalty, a.k.a the L2 penalty, a.k.a the square penalty,
75
the optimal slopes shift towards zero, but we retain a nice parabola shape.
76
And even when we set lambda to something crazy high like 400, we still end up with an optimal value greater than zero.
77
In contrast, when we increase the lasso penalty, a.k.a the L1 penalty, a.k.a the absolute value penalty,
78
The optimal value shifts towards zero, but since we have a kink at zero, zero ends up being the optimal slope.
79
Bam!
80
Hooray!
81
We've made it to the end of another exciting StatQuest.
82
If you like this StatQuest and want to see more, please subscribe.
83
And if you want to support StatQuest, consider contributing to my Patreon campaign,
84
becoming a channel member, buying one or two of my original songs or a t-shirt or a hoodie or just donate.
85
The links are in the description below.
86
All right, until next time, quest on!
Baixar aplicativo
Tudo o que você precisa para falar fluentemente
Pronúncia com IANota em cada frase
Prática de IPADomine cada som
VocabulárioMonte seu banco de palavras
Jogo de vocabulárioAprenda brincando
Mesmo canal
C17
Gaussian Naive Bayes, Clearly Explained!!!
Daily ConversationUniversity Students
C11
Naive Bayes, Clearly Explained!!!
Daily ConversationUniversity Students
C11
The Essential Main Ideas of Neural Networks
Business EnglishUniversity StudentsWorking Adults
C12
The GELU, SiLU and SwiGLU activation functions, clearly explained!!!
Daily ConversationUniversity Students
C11
A Gentle Introduction to Machine Learning
Business EnglishUniversity StudentsWorking Adults
FOR YOU
Vídeo recomendado
C11
64 frases
GCSE Physics - How to Draw Ray Diagrams - Concave & Convex Lenses (2027/28 exams)
Daily ConversationHigh School StudentsUniversity Students
C11
575 frases
Lec-6 Simplex Method | Maximization Problem | Mathematical Example Solution | Operations Research
Daily ConversationUniversity Students
C11
406 frases
Scoliosis: How to medically classify scoliosis (the Lenke System for AIS)
Daily ConversationUniversity Students
C11
847 frases
The Complete Guide to Hybrid Search in RAG (BM25 + Embeddings + Reranker)
Daily ConversationUniversity Students
C1287 frases
Differential equations, a tourist's guide | DE1
Daily ConversationUniversity Students
C11
167 frases
Mental Debugging: How to Build Resilience After Failure
Daily ConversationUniversity StudentsWorking Adults
C11
153 frases
Statics: Lesson 46 - Distributed Loads Using Centroids
Daily ConversationUniversity Students
C12
78 frases
Vanishing & Exploding Gradient explained | A problem resulting from backpropagation
Daily ConversationUniversity Students
C11
166 frases
The Scariest IQ Statistics | Jordan Peterson
Daily ConversationUniversity StudentsWorking Adults
C11
326 frases
Google Earth Engine Tutorial 1: Lake Area Estimation
Daily ConversationUniversity Students
C11
60 frases
Quick Study: How Venture Capitalists Make Decisions
Daily ConversationUniversity StudentsWorking Adults
Vocabulário e dicas de fala para esta lição
Esta aula de conversação usa o vídeo “Ridge vs Lasso Regression, Visualized!!!”. As palavras que mais se repetem: slope, penalty, lambda, equal, zero. Este vídeo tem 86 frases e 1111 palavras para praticar shadowing. A fala dura 9:04. O falante mantém um ritmo estável de cerca de 122 palavras por minuto, confortável para o shadowing. Apenas 70% das palavras estão entre as 3.000 mais comuns do inglês, por isso o vocabulário é exigente.
Vocabulário principal deste vídeo
15 palavras do vídeo que vale a pena aprender, com pronúncia e significado:
| Palavra | Pronúncia | Significado |
|---|---|---|
| slope substantivo | /sloʊp/ | ladeira, declive |
| penalty substantivo | /ˈpɛn.əl.ti/ | pena |
| optimal adjetivo | /ˈɑptɪməl/ | ótimo, óptimo |
| thick adjetivo | /θɪk/ | espesso, grosso |
| ridge substantivo | /ɹɪd͡ʒ/ | aresta, cresta |
| horizontal adjetivo | /ˌhoɹəˈzɑn.təl/ | horizontal |
| calculate verbo | /ˈkælkjʊleɪt/ | calcular |
| graph substantivo | /ɡɹæf/ | gráfico |
| curve substantivo | /kɚv/ | curva |
| purple substantivo | /ˈpɝ.pl̩/ | roxo, púrpura |
| plug substantivo | /plʌɡ/ | plugue |
| compare verbo | /kəmˈpɛɚ/ | comparar |
| versus | /ˈvɝsəs/ | contra, vérsus |
| quest substantivo | /kwɛst/ | busca |
| predict verbo | /pɹɪˈdɪkt/ | prever |
Phrasal verbs que você vai ouvir
| Palavra | Significado |
|---|---|
| check out verbo | verificar, sacar só |
| end up verbo | terminar, acabar |
Gramática neste vídeo
As estruturas que o falante mais usa, com as palavras exatas do vídeo:
| Estrutura | No vídeo |
|---|---|
| Voz passiva be + particípio passado — o foco está no que acontece, não em quem faz | be visualized · should be called · are left |
| Present perfect have/has + particípio passado — uma ação passada que ainda importa agora | has shrunk · We've made |
Pronúncia para ficar de olho
O falante usa 8 contrações e formas reduzidas, como we'll, we're, I'd. Diga-as na forma curta, do jeito que você ouve.
- Os sons de “sh” e “zh”: equation /ɪˈkweɪ.ʒən/, contrast /kənˈt(ʃ)ɹæst/, measurement /ˈmɛʒ.ə.mənt/, regression /ɹiːˈɡɹɛʃ.ən/, visualize /ˈvɪʒuəˌlaɪz/
- Palavras longas — acerte a sílaba tônica: residual /ɹɪˈzɪd͡ʒ.u.əl/, horizontal /ˌhoɹəˈzɑn.təl/, parabola /pəˈɹæb.ə.lə/
Sons difíceis para falantes de português:
- Consoante final — sem acrescentar um “i” depois: slope /sloʊp/, thick /θɪk/, calculate /ˈkælkjʊleɪt/, plug /plʌɡ/, quest /kwɛst/
- /l/ final — a língua toca o céu da boca, não vira “u”: residual /ɹɪˈzɪd͡ʒ.u.əl/, optimal /ˈɑptɪməl/, horizontal /ˌhoɹəˈzɑn.təl/
Como praticar com este vídeo
- Ouça o vídeo inteiro uma vez sem falar e anote as palavras que você não conhece.
- Faça shadowing frase por frase na velocidade normal, repetindo cada uma até o seu ritmo ficar igual ao do falante.
- Grave a sua voz e compare com o original, prestando atenção a palavras como slope, penalty, optimal.
O que é a Técnica de Shadowing?
Shadowing é uma técnica de aprendizado de idiomas com base científica, originalmente desenvolvida para o treinamento de intérpretes profissionais. O método é simples, mas poderoso: você ouve áudio em inglês nativo e repete imediatamente em voz alta — como uma sombra seguindo o falante com 1-2 segundos de atraso. Pesquisas mostram melhora significativa na precisão da pronúncia, entonação, ritmo, sons conectados, compreensão auditiva e fluência na fala.