RomanNum3ral
/
AI-For-Beginners
mirror of https://github.com/microsoft/AI-For-Beginners.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Finish quiz questions

This commit is contained in:
Dmitri Soshnikov 2022-05-24 19:30:25 +03:00
parent 7da83534e3
commit 61c80d74a5
13 changed files with 926 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
etc/quiz-app/src/assets/translations/en/index.js
View File

@ -8,13 +8,19 @@ import x7 from "./lesson-7.json";
import x8 from "./lesson-8.json";
import x9 from "./lesson-9.json";
import x10 from "./lesson-10.json";
import x11 from "./lesson-11.json";
import x12 from "./lesson-12.json";
import x13 from "./lesson-13.json";
import x14 from "./lesson-14.json";
import x15 from "./lesson-15.json";
import x16 from "./lesson-16.json";
import x17 from "./lesson-17.json";
import x18 from "./lesson-18.json";
import x19 from "./lesson-19.json";
import x20 from "./lesson-20.json";
import x21 from "./lesson-21.json";
import x22 from "./lesson-22.json";
import x23 from "./lesson-23.json";
const quiz = { 0 : x1[0], 1 : x2[0], 2 : x3[0], 3 : x4[0], 4 : x5[0], 5 : x6[0], 6 : x7[0], 7 : x8[0], 8 : x9[0], 9 : x10[0], 10 : x12[0], 11 : x13[0], 12 : x14[0], 13 : x16[0], 14 : x17[0], 15 : x18[0], 16 : x21[0], 17 : x23[0] };
import x24 from "./lesson-24.json";
const quiz = { 0 : x1[0], 1 : x2[0], 2 : x3[0], 3 : x4[0], 4 : x5[0], 5 : x6[0], 6 : x7[0], 7 : x8[0], 8 : x9[0], 9 : x10[0], 10 : x11[0], 11 : x12[0], 12 : x13[0], 13 : x14[0], 14 : x15[0], 15 : x16[0], 16 : x17[0], 17 : x18[0], 18 : x19[0], 19 : x20[0], 20 : x21[0], 21 : x22[0], 22 : x23[0], 23 : x24[0] };
export default quiz;

119
etc/quiz-app/src/assets/translations/en/lesson-11.json Normal file
View File

@ -0,0 +1,119 @@
[
{
"title": "AI for Beginners: Quizzes",
"complete": "Congratulations, you completed the quiz!",
"error": "Sorry, try again",
"quizzes": [
{
"id": 111,
"title": "Object Detection: Pre Quiz",
"quiz": [
{
"questionText": "Neural networks can only be used to classify images",
"answerOptions": [
{
"answerText": "true",
"isCorrect": false
},
{
"answerText": "false",
"isCorrect": true
}
]
},
{
"questionText": "With object detection, we don't just get class of an object, but also it's ____",
"answerOptions": [
{
"answerText": "shape",
"isCorrect": false
},
{
"answerText": "location",
"isCorrect": true
},
{
"answerText": "type",
"isCorrect": false
}
]
},
{
"questionText": "How many objects an object detection model can detect?",
"answerOptions": [
{
"answerText": "one",
"isCorrect": false
},
{
"answerText": "two",
"isCorrect": false
},
{
"answerText": "any number",
"isCorrect": true
}
]
}
]
},
{
"id": 211,
"title": "Object Detection: Post Quiz",
"quiz": [
{
"questionText": "Object detection model give us",
"answerOptions": [
{
"answerText": "object class",
"isCorrect": false
},
{
"answerText": "bounding box",
"isCorrect": false
},
{
"answerText": "both class and bounding box",
"isCorrect": true
}
]
},
{
"questionText": "Which object detection models are faster?",
"answerOptions": [
{
"answerText": "one-pass models",
"isCorrect": true
},
{
"answerText": "region proposal networks",
"isCorrect": false
},
{
"answerText": "Fast R-CNN",
"isCorrect": false
}
]
},
{
"questionText": "Which metric can be used to determine how well bounding boxes are aligned?",
"answerOptions": [
{
"answerText": "accuracy",
"isCorrect": false
},
{
"answerText": "precision",
"isCorrect": false
},
{
"answerText": "IoU",
"isCorrect": true
}
]
}
]
}
]
}
]

2
etc/quiz-app/src/assets/translations/en/lesson-12.json
View File

@ -50,7 +50,7 @@
"isCorrect": false
},
{
"answerText": "encoder, Decoder",
"answerText": "encoder, decoder",
"isCorrect": true
},
{

123
etc/quiz-app/src/assets/translations/en/lesson-15.json Normal file
View File

@ -0,0 +1,123 @@
[
{
"title": "AI for Beginners: Quizzes",
"complete": "Congratulations, you completed the quiz!",
"error": "Sorry, try again",
"quizzes": [
{
"id": 115,
"title": "Language Modeling: Pre Quiz",
"quiz": [
{
"questionText": "Which of the following can be considered a language model?",
"answerOptions": [
{
"answerText": "Word2Vec embeddings",
"isCorrect": true
},
{
"answerText": "Embedding layer in RNN",
"isCorrect": false
},
{
"answerText": "RNN used for text classification",
"isCorrect": false
}
]
},
{
"questionText": "A language model should be able to ____ the next word in the sentence",
"answerOptions": [
{
"answerText": "use",
"isCorrect": false
},
{
"answerText": "predict",
"isCorrect": true
},
{
"answerText": "guess",
"isCorrect": false
}
]
},
{
"questionText": "Language models are trained on",
"answerOptions": [
{
"answerText": "language vocabulary",
"isCorrect": false
},
{
"answerText": "specially labeled data",
"isCorrect": false
},
{
"answerText": "any natural text",
"isCorrect": true
}
]
}
]
},
{
"id": 215,
"title": "Language Modeling: Post Quiz",
"quiz": [
{
"questionText": "Which of the architectures predicts a word from neighboring words?",
"answerOptions": [
{
"answerText": "CBoW",
"isCorrect": true
},
{
"answerText": "Skip-gram",
"isCorrect": false
},
{
"answerText": "N-Gram",
"isCorrect": false
}
]
},
{
"questionText": "When we train CBoW model, we obtain",
"answerOptions": [
{
"answerText": "A model that can generate text",
"isCorrect": false
},
{
"answerText": "Word2Vec embedding vectors",
"isCorrect": true
},
{
"answerText": "Text classification model",
"isCorrect": false
}
]
},
{
"questionText": "CBoW model is based on",
"answerOptions": [
{
"answerText": "Dense neural network",
"isCorrect": true
},
{
"answerText": "Convolutional neural network",
"isCorrect": false
},
{
"answerText": "Recurrent neural network",
"isCorrect": false
}
]
}
]
}
]
}
]

2
etc/quiz-app/src/assets/translations/en/lesson-16.json
View File

@ -66,7 +66,7 @@
"title": "RNN: Post Quiz",
"quiz": [
{
"questionText": "_____ takes some information from the input and hidden vector, and inserts it into the state",
"questionText": "_____ takes some information from the input and hidden vector, and inserts it into state",
"answerOptions": [
{
"answerText": "forget gate",

4
etc/quiz-app/src/assets/translations/en/lesson-17.json
View File

@ -39,7 +39,7 @@
]
},
{
"questionText": "RNN generates texts by generating the next output character for each input character",
"questionText": "RNN generates texts by generating next output token for each input token",
"answerOptions": [
{
"answerText": "true",
@ -58,7 +58,7 @@
"title": "Generative networks: Post Quiz",
"quiz": [
{
"questionText": "An output encoder converts hidden state into _____ output",
"questionText": "Output encoder converts hidden state into _____ output",
"answerOptions": [
{
"answerText": "one-hot-encoded",

2
etc/quiz-app/src/assets/translations/en/lesson-18.json
View File

@ -9,7 +9,7 @@
"title": "Transformers: Pre Quiz",
"quiz": [
{
"questionText": "Attention mechanism provides a means of _____ the impact of an inout vector on an output prediction of RNN",
"questionText": "Attention mechanism provides a means of _____ the imoact of an inout vector on an output prediction of RNN",
"answerOptions": [
{
"answerText": "weighting",

119
etc/quiz-app/src/assets/translations/en/lesson-19.json Normal file
View File

@ -0,0 +1,119 @@
[
{
"title": "AI for Beginners: Quizzes",
"complete": "Congratulations, you completed the quiz!",
"error": "Sorry, try again",
"quizzes": [
{
"id": 119,
"title": "Named Entity Recognition: Pre Quiz",
"quiz": [
{
"questionText": "What is NER stands for?",
"answerOptions": [
{
"answerText": "Nearest Estimated Region",
"isCorrect": false
},
{
"answerText": "Nearest Entity Region",
"isCorrect": false
},
{
"answerText": "Named Entity Recognition",
"isCorrect": true
}
]
},
{
"questionText": "An entity always consists of one token",
"answerOptions": [
{
"answerText": "true",
"isCorrect": false
},
{
"answerText": "false",
"isCorrect": true
}
]
},
{
"questionText": "To train NER model, we need",
"answerOptions": [
{
"answerText": "Labeled dataset",
"isCorrect": true
},
{
"answerText": "Any natural text",
"isCorrect": false
},
{
"answerText": "Translated texts in two languages",
"isCorrect": false
}
]
}
]
},
{
"id": 219,
"title": "Named Entity Recognition: Post Quiz",
"quiz": [
{
"questionText": "NER model is essentially a ____ model",
"answerOptions": [
{
"answerText": "text classification",
"isCorrect": false
},
{
"answerText": "token classification",
"isCorrect": false
},
{
"answerText": "text regression",
"isCorrect": false
}
]
},
{
"questionText": "Which neural network types can be used for NER?",
"answerOptions": [
{
"answerText": "RNNs",
"isCorrect": false
},
{
"answerText": "Transformers",
"isCorrect": false
},
{
"answerText": "Both RNNs and Transformers",
"isCorrect": true
}
]
},
{
"questionText": "NER model is a good example of ____ network architecture",
"answerOptions": [
{
"answerText": "one-to-one",
"isCorrect": false
},
{
"answerText": "one-to-many",
"isCorrect": false
},
{
"answerText": "many-to-many",
"isCorrect": true
}
]
}
]
}
]
}
]

119
etc/quiz-app/src/assets/translations/en/lesson-20.json Normal file
View File

@ -0,0 +1,119 @@
[
{
"title": "AI for Beginners: Quizzes",
"complete": "Congratulations, you completed the quiz!",
"error": "Sorry, try again",
"quizzes": [
{
"id": 120,
"title": "Language Models: Pre Quiz",
"quiz": [
{
"questionText": "What is GPT stands for?",
"answerOptions": [
{
"answerText": "Generic Pre-Trained network",
"isCorrect": false
},
{
"answerText": "Generative Pre-trained Transformers",
"isCorrect": true
},
{
"answerText": "Generic Positional Text",
"isCorrect": false
}
]
},
{
"questionText": "What can GPT be used for?",
"answerOptions": [
{
"answerText": "Text generation",
"isCorrect": false
},
{
"answerText": "Text classification",
"isCorrect": false
},
{
"answerText": "Both text generation and other tasks",
"isCorrect": true
}
]
},
{
"questionText": "GPT is based on transformer architecture",
"answerOptions": [
{
"answerText": "true",
"isCorrect": true
},
{
"answerText": "false",
"isCorrect": false
}
]
}
]
},
{
"id": 220,
"title": "Language Models: Post Quiz",
"quiz": [
{
"questionText": "What is zero-shot learning?",
"answerOptions": [
{
"answerText": "Getting an answer from pre-trained network",
"isCorrect": true
},
{
"answerText": "Training the network from scratch",
"isCorrect": false
},
{
"answerText": "Training the network only for one epoch",
"isCorrect": false
}
]
},
{
"questionText": "Prompt engineering can be used with",
"answerOptions": [
{
"answerText": "Zero-shot learning",
"isCorrect": false
},
{
"answerText": "Few-shot learning",
"isCorrect": false
},
{
"answerText": "Both",
"isCorrect": false
}
]
},
{
"questionText": "Which metric can be used to estimate quality of a language model?",
"answerOptions": [
{
"answerText": "accuracy",
"isCorrect": false
},
{
"answerText": "recall",
"isCorrect": false
},
{
"answerText": "perplexity",
"isCorrect": true
}
]
}
]
}
]
}
]

123
etc/quiz-app/src/assets/translations/en/lesson-22.json Normal file
View File

@ -0,0 +1,123 @@
[
{
"title": "AI for Beginners: Quizzes",
"complete": "Congratulations, you completed the quiz!",
"error": "Sorry, try again",
"quizzes": [
{
"id": 122,
"title": "Reinforcement Learning: Pre Quiz",
"quiz": [
{
"questionText": "To train RL model, we need",
"answerOptions": [
{
"answerText": "Simulation environment",
"isCorrect": true
},
{
"answerText": "Labeled dataset",
"isCorrect": false
},
{
"answerText": "Unlabeled dataset",
"isCorrect": false
}
]
},
{
"questionText": "What is a good example of Reinforcement learning:",
"answerOptions": [
{
"answerText": "Zero-shot image classification",
"isCorrect": false
},
{
"answerText": "Zero-shot text classification",
"isCorrect": false
},
{
"answerText": "Learning to play chess",
"isCorrect": true
}
]
},
{
"questionText": "When creating RL-based chess engine, we need to",
"answerOptions": [
{
"answerText": "use all existing chess matches as a dataset",
"isCorrect": false
},
{
"answerText": "let computer play against itself many times",
"isCorrect": true
},
{
"answerText": "program exhaustive search algorithm",
"isCorrect": false
}
]
}
]
},
{
"id": 222,
"title": "Reinforcement Learning: Post Quiz",
"quiz": [
{
"questionText": "How does RL training algorithm knows how well it did?",
"answerOptions": [
{
"answerText": "It achieves high accuracy",
"isCorrect": false
},
{
"answerText": "Using perplexity metric",
"isCorrect": false
},
{
"answerText": "Using reward function",
"isCorrect": true
}
]
},
{
"questionText": "Which problems RL is applicable to?",
"answerOptions": [
{
"answerText": "With discrete environment",
"isCorrect": false
},
{
"answerText": "With continuous environment",
"isCorrect": false
},
{
"answerText": "Both",
"isCorrect": true
}
]
},
{
"questionText": "In Actor-Critic model, critic predicts",
"answerOptions": [
{
"answerText": "Reward function",
"isCorrect": true
},
{
"answerText": "Best next action",
"isCorrect": false
},
{
"answerText": "Probability of next actions",
"isCorrect": false
}
]
}
]
}
]
}
]

2
etc/quiz-app/src/assets/translations/en/lesson-23.json
View File

@ -107,7 +107,7 @@
"isCorrect": false
},
{
"answerText": "both of the above",
"answerText": "both the above",
"isCorrect": true
}
]

136
etc/quiz-app/src/assets/translations/en/lesson-24.json Normal file
View File

@ -0,0 +1,136 @@
[
{
"title": "AI for Beginners: Quizzes",
"complete": "Congratulations, you completed the quiz!",
"error": "Sorry, try again",
"quizzes": [
{
"id": 124,
"title": "Ethical and Responsible AI: Pre Quiz",
"quiz": [
{
"questionText": "Why we need to worry about Ethical AI?",
"answerOptions": [
{
"answerText": "AI is a very powerful tool and can cause harm",
"isCorrect": false
},
{
"answerText": "We need to make sure AI models do not discriminate people",
"isCorrect": false
},
{
"answerText": "Both",
"isCorrect": true
}
]
},
{
"questionText": "Which is the example of interpretable AI?",
"answerOptions": [
{
"answerText": "Expert system",
"isCorrect": true
},
{
"answerText": "Neural network",
"isCorrect": false
},
{
"answerText": "Image classifier",
"isCorrect": false
}
]
},
{
"questionText": "It is not ethical to use AI in medicine",
"answerOptions": [
{
"answerText": "true",
"isCorrect": false
},
{
"answerText": "false",
"isCorrect": true
}
]
}
]
},
{
"id": 224,
"title": "Ethical and Responsible AI: Post Quiz",
"quiz": [
{
"questionText": "Why an AI model can discriminate?",
"answerOptions": [
{
"answerText": "Because it may become unfriendly",
"isCorrect": false
},
{
"answerText": "Because datasets were not properly balanced",
"isCorrect": true
},
{
"answerText": "Because developers programmed it in such a way",
"isCorrect": false
}
]
},
{
"questionText": "Which of the following is not a principle of Responsible AI?",
"answerOptions": [
{
"answerText": "Transparency",
"isCorrect": false
},
{
"answerText": "Fairness",
"isCorrect": false
},
{
"answerText": "Cleverness",
"isCorrect": true
}
]
},
{
"questionText": "Accountability of an AI system means that",
"answerOptions": [
{
"answerText": "there should be a human being involved in taking decisions, who can take responsibility",
"isCorrect": true
},
{
"answerText": "AI system should be held responsible for its actions",
"isCorrect": false
},
{
"answerText": "AI system developers should be held responsible",
"isCorrect": false
}
]
},
{
"questionText": "Model fairness is related to",
"answerOptions": [
{
"answerText": "Interpretability",
"isCorrect": false
},
{
"answerText": "Biases",
"isCorrect": true
},
{
"answerText": "Accountability",
"isCorrect": false
}
]
}
]
}
]
}
]

180
etc/quiz-src/questions-en.txt
View File

@ -258,6 +258,33 @@ Lesson 10E Generative Adversarial Networks: Post Quiz
- Keeping balance between generator and discriminator
+ all of the above
Lesson 11B Object Detection: Pre Quiz
* Neural networks can only be used to classify images
- true
+ false
* With object detection, we don't just get class of an object, but also it's ____
- shape
+ location
- type
* How many objects an object detection model can detect?
- one
- two
+ any number
Lesson 11E Object Detection: Post Quiz
* Object detection model give us
- object class
- bounding box
+ both class and bounding box
* Which object detection models are faster?
+ one-pass models
- region proposal networks
- Fast R-CNN
* Which metric can be used to determine how well bounding boxes are aligned?
- accuracy
- precision
+ IoU
Lesson 12B Segmentation: Pre Quiz
* There are ____ segmentation algorithms?
- 1
@ -269,7 +296,7 @@ Lesson 12B Segmentation: Pre Quiz
- neural networks
* Segmentation networks consist of ____ and ____ parts
- classifier, divider
+ encoder, Decoder
+ encoder, decoder
- generator, discriminator
Lesson 12E Segmentation: Post Quiz
@ -337,6 +364,34 @@ Lesson 14E Embeddings: Post Quiz
- symbol
- number
Lesson 15B Language Modeling: Pre Quiz
* Which of the following can be considered a language model?
+ Word2Vec embeddings
- Embedding layer in RNN
- RNN used for text classification
* A language model should be able to ____ the next word in the sentence
- use
+ predict
- guess
* Language models are trained on
- language vocabulary
- specially labeled data
+ any natural text
Lesson 15E Language Modeling: Post Quiz
* Which of the architectures predicts a word from neighboring words?
+ CBoW
- Skip-gram
- N-Gram
* When we train CBoW model, we obtain
- A model that can generate text
+ Word2Vec embedding vectors
- Text classification model
* CBoW model is based on
+ Dense neural network
- Convolutional neural network
- Recurrent neural network
Lesson 16B RNN: Pre Quiz
* RNN is short for?
- regression neural network
@ -352,7 +407,7 @@ Lesson 16B RNN: Pre Quiz
- KNN
Lesson 16E RNN: Post Quiz
* _____ takes some information from the input and hidden vector, and inserts it into the state
* _____ takes some information from the input and hidden vector, and inserts it into state
- forget gate
- output gate
+ input gate
@ -372,12 +427,12 @@ Lesson 17B Generative networks: Pre Quiz
+ one-to-one
- sequence-to-sequence
- one-to-many
* RNN generates texts by generating the next output character for each input character
* RNN generates texts by generating next output token for each input token
+ true
- false
Lesson 17E Generative networks: Post Quiz
* An output encoder converts hidden state into _____ output
* Output encoder converts hidden state into _____ output
+ one-hot-encoded
- sequence
- number
@ -391,7 +446,7 @@ Lesson 17E Generative networks: Post Quiz
- one-to-many
Lesson 18B Transformers: Pre Quiz
* Attention mechanism provides a means of _____ the impact of an inout vector on an output prediction of RNN
* Attention mechanism provides a means of _____ the imoact of an inout vector on an output prediction of RNN
+ weighting
- training
- testing
@ -417,6 +472,60 @@ Lesson 18E Transformers: Post Quiz
+ 2
- 3
Lesson 19B Named Entity Recognition: Pre Quiz
* What is NER stands for?
- Nearest Estimated Region
- Nearest Entity Region
+ Named Entity Recognition
* An entity always consists of one token
- true
+ false
* To train NER model, we need
+ Labeled dataset
- Any natural text
- Translated texts in two languages
Lesson 19E Named Entity Recognition: Post Quiz
* NER model is essentially a ____ model
- text classification
- token classification
- text regression
* Which neural network types can be used for NER?
- RNNs
- Transformers
+ Both RNNs and Transformers
* NER model is a good example of ____ network architecture
- one-to-one
- one-to-many
+ many-to-many
Lesson 20B Language Models: Pre Quiz
* What is GPT stands for?
- Generic Pre-Trained network
+ Generative Pre-trained Transformers
- Generic Positional Text
* What can GPT be used for?
- Text generation
- Text classification
+ Both text generation and other tasks
* GPT is based on transformer architecture
+ true
- false
Lesson 20E Language Models: Post Quiz
* What is zero-shot learning?
+ Getting an answer from pre-trained network
- Training the network from scratch
- Training the network only for one epoch
* Prompt engineering can be used with
- Zero-shot learning
- Few-shot learning
- Both
* Which metric can be used to estimate quality of a language model?
- accuracy
- recall
+ perplexity
Lesson 21B Genetic Algorithms: Pre Quiz
* Genetic Algorithms are based on which of the following?
- mutations
@ -443,6 +552,34 @@ Lesson 21E Genetic Algorithms: Post Quiz
- 1
+ 2
Lesson 22B Reinforcement Learning: Pre Quiz
* To train RL model, we need
+ Simulation environment
- Labeled dataset
- Unlabeled dataset
* What is a good example of Reinforcement learning:
- Zero-shot image classification
- Zero-shot text classification
+ Learning to play chess
* When creating RL-based chess engine, we need to
- use all existing chess matches as a dataset
+ let computer play against itself many times
- program exhaustive search algorithm
Lesson 22E Reinforcement Learning: Post Quiz
* How does RL training algorithm knows how well it did?
- It achieves high accuracy
- Using perplexity metric
+ Using reward function
* Which problems RL is applicable to?
- With discrete environment
- With continuous environment
+ Both
* In Actor-Critic model, critic predicts
+ Reward function
- Best next action
- Probability of next actions
Lesson 23B Multi-Agent Modeling: Pre Quiz
* By modeling the behavior of simple agents, we can understand more complex behaviors of a system.
+ true
@ -468,4 +605,35 @@ Lesson 23E Multi-Agent Modeling: Post Quiz
* Multi-agent systems are used in:
- video production and systems modeling
- games and automations
+ both of the above
+ both the above
Lesson 24B Ethical and Responsible AI: Pre Quiz
* Why we need to worry about Ethical AI?
- AI is a very powerful tool and can cause harm
- We need to make sure AI models do not discriminate people
+ Both
* Which is the example of interpretable AI?
+ Expert system
- Neural network
- Image classifier
* It is not ethical to use AI in medicine
- true
+ false
Lesson 24E Ethical and Responsible AI: Post Quiz
* Why an AI model can discriminate?
- Because it may become unfriendly
+ Because datasets were not properly balanced
- Because developers programmed it in such a way
* Which of the following is not a principle of Responsible AI?
- Transparency
- Fairness
+ Cleverness
* Accountability of an AI system means that
+ there should be a human being involved in taking decisions, who can take responsibility
- AI system should be held responsible for its actions
- AI system developers should be held responsible
* Model fairness is related to
- Interpretability
+ Biases
- Accountability