텍스트 생성 모델

텍스트 생성 모델

11th Grade

5 Qs

quiz-placeholder

Similar activities

TES PENGETAHUAN KD 3.3 ROUTING

TES PENGETAHUAN KD 3.3 ROUTING

11th Grade

10 Qs

Onshape - Intro to CAD - Unit 1 Vocab

Onshape - Intro to CAD - Unit 1 Vocab

9th - 12th Grade

10 Qs

DAMPAK SOSIAL INFORMATIKA

DAMPAK SOSIAL INFORMATIKA

9th - 12th Grade

10 Qs

DESAIN PUBLIKASI

DESAIN PUBLIKASI

11th Grade

10 Qs

Python Testing

Python Testing

9th - 12th Grade

10 Qs

ADMIN SISTEM JARINGAN - XI TKJ-GANJIL

ADMIN SISTEM JARINGAN - XI TKJ-GANJIL

11th Grade

10 Qs

Weekly Quiz 1

Weekly Quiz 1

4th Grade - Professional Development

10 Qs

ม.5 แบบทดสอบก่อนเรียน หน่วยที่ 1

ม.5 แบบทดสอบก่อนเรียน หน่วยที่ 1

11th Grade

10 Qs

텍스트 생성 모델

텍스트 생성 모델

Assessment

Quiz

Computers

11th Grade

Practice Problem

Hard

Created by

S Chung

Used 3+ times

FREE Resource

AI

Enhance your content in a minute

Add similar questions
Adjust reading levels
Convert to real-world scenario
Translate activity
More...

5 questions

Show all answers

1.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

다음 중 장단기 메모리 모델은?

NN

CNN

RNN

LSTM

2.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

다음 중 장단기 메모리 모델 구성 과정에서 ①에 들어갈 단어는?

model = Sequential()

model.add( ① (128, input_shape = (maxlen, len(chars))))

model.add( ② (len(chars), activation = 'softmax'))

NN

CNN

Dense

LSTM

3.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

다음 중 장단기 메모리 모델 구성 과정에서 ②에 들어갈 단어는?

model = Sequential()

model.add( ① (128, input_shape = (maxlen, len(chars))))

model.add( ② (len(chars), activation = 'softmax'))

NN

CNN

Dense

LSTM

4.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

다음 중 모델 컴파일에 해당하는 것은?

model = Sequential()

model.add(Dense(len(chars), activation = 'softmax'))

model.compile(loss = 'categorical_crossentropy', optimizer = 'RMSprop')

model.fit(x, y, batch_size = 128, epochs = 1)

5.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

다음 중 모델 학습에 해당하는 것은?

model = Sequential()

model.add(Dense(len(chars), activation = 'softmax'))

model.compile(loss = 'categorical_crossentropy', optimizer = 'RMSprop')

model.fit(x, y, batch_size = 128, epochs = 1)