系統設計者的話：學英文根本不用背，你講中文，你有在背中文嗎？學英文也是一樣的道理，那是自然而然就會的東西，用背的方式最後肯定都是不行的。更多...

最好的學習就是有英文的父母，不斷的跟你說話、耐心的教導你，時間長了，你也就慢慢就融入其中了。

但是我們沒有英文父母怎麼辦？看影片學英文就學的起來嗎？學不起來。

我們從小到大，也看過了不少英文電影，至少也看過1、200部也跑不掉，但是為什麼看了這麼多的英文電影，英文還是很爛呢？

主要的原因是我們沒有從基礎性的強化學習。舉個例子，西方的幼兒出生時，他至少聽了各種大人講英文至少聽了2年，才慢慢開始說英文、與大人互動。

而且都是一字一句慢慢的說、慢慢的教、漸進式的、慢慢的、越來越習慣、越來越聽的懂、越來越會說的過程。

那麼我們看的影片、電影過程中，都是大人成熟型的講話速度、方式、語調，我們怎麼可能跟的上？

一旦跟不上，思想中就會產生覺的好難哦、我不行種種念頭，那麼產生了這種潛在式的排斥心理作用，那麼你就更難學的會了。

所以我們必須打好基礎、深厚的基礎，萬丈高樓平地起，唯有打下深厚的基礎，後面你走的路才會越來越順。

程式界裏有句話，程式債欠的越多，最後就只能放棄。學英文也是一樣，英文單字債欠的越多，你就直接上來文法、句型、語調，最後也只能放棄。

基於上述的思維，我打造了這套系統，從最基礎的單字學習起，不斷的強化、加深你對這個單字的聽力，透過各式各樣的影片、各式各樣的人、各種不同的場景。

就只是為了訓練一個單字的聽力，無數的人跟你講同一個單字，講個20遍、50篇、100遍(且不重覆)，我就不信學不起來。

這套系統做出來後，我自己在使用的過程中，確實真的能聽出來他們講的這個單字，而且他們講的速度再快也能聽的出來。

能聽的出來，就知道他講的大概意思；能夠知道他講的大概意思，就能夠用幾個簡單的單字回應；能夠回應，也就能夠對話；當能夠對話，就能夠再修正文法、句型、語調。

我的目地就是希望自己至少能聽的懂人家在說什麼，用英文跟人家對話，大家共同努力、學習。若有其它想法或對這套系統設計的建議，也可以與我聯絡：ichich2013@gmail.com

TF Machine Learning for Programmers (TensorFlow @ O’Reilly AI Conference, San Francisco '18)

觀看次數：416

播放速度:

righty

i'm

sensor

flow

flow

programmers

programmers

i'd

tensor

flow

scenarios

contents

you've

conferences

there's

there's

programmers

scenarios

we're

cusp

it's

it's

mid

90s

programmers

programming

wasn't

runtime

there's

browser

browser

plugins

java

paradigm

industries

weren't

gophers

that's

old-school

gophers

gopher

nascent

let's

let's

flip

axes

paradigm

yahoo

ditto

wouldn't

browser

pre

twitter

wasn't

tectonic

smartphone

that's

computational

it's

it's

it's

sensors

etc

it's

uber

i'm

introverts

you'll

it's

introverts

i'm

introverted

uber

it's

it's

i'm

introverted

it's

it's

don't

it's

it's

it's

tectonic

i'm

there's

hype

hype

hype

hype

that's

universities

it's

it's

tensorflow

i'm

neural

networks

neural

networks

universities

traeger

that's

hype

everybody's

be-all

end-all

disillusionment

revolutions

lifecycle

you've

i'm

we're

loosely

glossy

videos

isn't

it's

neural

networks

programming

who've

scenarios

we're

we're

disillusionment

you'll

uber

don't

hyper

coding

it's

solves

expressing

java

c++

it's

scenarios

i'm

i'm

i'm

explicitly

programming

coders

c-sharp

-

i've

c-sharp

don't

that's

c-sharp

python

c++

you're

you're

i'm

smartwatch

smartwatches

smartwatch

monitors

i'm

logs

i'm

calories

coding

smartwatch

you're

coder

person's

you're

person's

that's

naive

you're

uphill

you're

you're

you're

i'll

i'm

i'm

i'm

i'm

i've

detects

i'm

i'm

biking

i'm

i'm

i'm

biking

i've

naive

person's

he's

i'm

i'm

i'm

programmer

i've

i'm

can't

doesn't

i've

uber

wouldn't

wouldn't

wouldn't

programming

programming

programming

c-sharp

that's

you're

you're

you're

flips

axes

i'm

i'm

i'm

i'm

it's

it's

i'm

sensor

it's

smartphone

i'm

i'm

i'm

i'm

biking

golfing

expandable

detecting

i've

scenarios

if-then

prolog

prolog

couldn't

prolog

emulates

recognizes

i'm

that's

crosses

nodding

tic-tac-toe

japan

couldn't

it's

it's

you're

doesn't

they're

learns

they've

left-hand

para

lensses

labelled

that's

labeled

labeled

they'll

labeled

examples

labeled

examples

it's

tic-tac-toe

crosses

let's

tic-tac-toe

you've

don't

don't

sill

don't

if-then

didn't

didn't

that's

learns

neural

runtime

classifications

predictions

you've

let's

programmers

i'm

i'm

there's

let's

here's

1

y

3

y

1

etc

etc

y

y

equals

y

1

y

equals

2x

1

what's

can't

you've

there's

y

equals

mx

plugging

msc

y

3

that's

x's

2

i'll

3

i'll

0

&

1

1

1

y

that's

neural

that's

neural

neural

it's

4

calculating

that's

cycles

gpu

let's

tensorflow

don't

tensorflow

here's

i'm

neural

i'm

i'm

neural

neural

it's

neuron

layers

equals

1

equals

1

that's

i'm

i'm

neuron

i'm

you're

neural

guesses

functions

what's

optimizer

they're

it's

y

equals

i'm

something's

i'm

y's

i'm

i'm

i'm

something's

it's

optimizer

here's

i'm

i'll

y

equals

2x

1

that's

optimizer

cara's

tensorflow

they're

you're

i'm

i'm

squared

errors

i'm

sgd

stochastic

optimizer

it's

i'm

neural

i'm

x's

1

0

1

etc

y's

i'm

rays

python

i'm

neural

x's

y's

epochs

equals

500

you're

500

it's

500

it's

it's

optimize

it's

it's

optimize

i'm

500

500

it's

it's

y

10

2x

1

19

doesn't

it'll

19

i'm

what's

it's

predicting

it's

it's

there's

there's

i'm

factored

you'll

it's

it's

it's

i'm

it's

foo

let's

here's

it's

500

epochs

predicts

i'm

it's

pycharm

neural

epochs

neural

basics

slides

whoops

java

c-sharp

python

c++

300

programming

mfc

15

let's

let's

you're

you've

instantly

instantly

sneaker

vaguely

high-heeled

sneaker

automatically

doesn't

automatically

it's

it's

t-shirt

differences

it's

high-heeled

sneaker

there's

70000

it's

labeled

70000

10

classes

handbags

it's

28

28

pixels

it's

you're

high-definition

handbags

that's

they've

neural

28

28

pixel

you're

handbags

here's

item

28

28

pixels

automatically

it's

classifier

let's

neural

compiled

neural

specifying

optimizer

codes

you're

tensorflow

flow

you're

import

namespace

namespace

emne

70000

coding

that's

python

python

it's

equals

that's

it's

stored

it's

sorting

70

60000

60000

10000

10000

you're

clues

neural

you've

i'm

it's

that's

that's

that's

labeled

that's

let's

knurl

rounds

28

28

pixels

you're

9

brogue

that's

gaelic

i'm

biased

classifier

that's

let's

defining

neural

neuron

it's

classifier

layers

layers

flatten

equals

28

28

i'm

defining

28

squared

28

28

pixels

don't

neural

0

255

nons

there's

activation

we'll

neurons

28

squared

10

10

10

classes

neural

it's

it's

outputs

neuron

neuron

neuron

neuron

outputs

neurons

neural

it's

we're

i'm

encode

we'll

neuron

what's

activation

it's

mathlete

programmers

tf

rella

encode

that's

that's

filtered

neurons

that's

filtered

neural

they're

don't

neural

there's

activation

relu

you'll

rel

matthew

you'll

relu

you'll

greek

don't

it's

i've

defined

neural

i'm

you'll

i'm

neural

compiling

neural

optimizer

there's

functions

there's

optimizer

functions

categorical

cross-entropy

optimizer

optimizer

programmer

optimizer

neural

there's

it's

coder

you're

neural

networks

there's

you'll

selecting

functions

you'll

functions

i'm

optimizer

it's

it's

it's

i'll

i'll

optimizer

weights

neural

that's

optimizer

it's

optimization

categorical

categorical

entropy

it's

it's

duc

i'm

outfits

i'm

i'm

i'm

epochs

epochs

it's

you'll

you're

you'll

converging

you'll

convergence

epochs

you'll

epochs

neural

defined

epochs

iterate

10000

it's

improves

decreases

60000

10000

looping

righty

formatted

28

28

grayscale

it'll

predictions

predictions

neural

10

layers

10

10

that's

item

let's

it's

i'm

there's

i'm

it's

here's

slides

i'm

there's

i've

didn't

slides

scales

pixel

256

neural

normalize

255

it's

0

1

that's

codes

that's

python

60000

28

28

255

normalized

that's

python

it's

i'm

10000

0

99

99

don't

what's

what's

27

that's

27

27

27

4

5

6

0

what's

i'm

neural

they're

27

it's

it's

you'll

27

item

27

there's

pre

it'll

predicted

there's

90%

it's

it's

i'm

debug

epochs

it's

89%

it's

they're

item

27

they're

predicted

what's

42

that's

42

i'm

42

item

let's

haven't

bracketing

it's

it's

there's

let's

i'm

epochs

i'm

convergence

82%

42

predicted

it's

82%

86%

eighty-seven

89

epochs

don't

42

douglas

adams's

you've

doesn't

that's

ford

programmers

you've

programming

demonstrates

didn't

t-shirt

sleeves

sleeves

t-shirt

didn't

相關影片

加Line好友每日8AM 推播1單字

其他人正在學習的單字

1. had

2024-04-28 08:28

2024-04-28 08:28

2024-04-28 08:27

2024-04-28 08:27

2024-04-28 08:27

6. yes

2024-04-28 08:27

7. let

2024-04-28 08:27

2024-04-28 08:27

2024-04-28 08:27

10. come

2024-04-28 08:27

2024-04-28 08:27

2024-04-28 08:27

2024-04-28 08:27

14. oh

2024-04-28 08:26

2024-04-28 08:26

本月觀看影片單字排行榜

本月查閱單字排行榜

本月聆聽單字排行榜