Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Introduction to Machine Learning > AWS Machine Learning Foundations Course - Lesson 3 > Flashcards

AWS Machine Learning Foundations Course - Lesson 3 Flashcards

1
Q

What is a machine learning task

A

The outputs of model training algorithms are classified based on the task they are designed to solve

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

How do you determine which machine learning task to use

A

The absence or presence of labeling in the the data is used to identify the machine learning task to use

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are the three components of machine learning

A
  1. A machine learning model
  2. A model training algorithm
  3. A model inference algorithm
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What are the five machine learning steps

A
  1. Define the problem
  2. Build the dataset
  3. Train the model
  4. Evaluate the model
  5. Deploy/use the model
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What are the four main machine learning tasks

A
  1. Supervised
  2. Unsupervised
  3. Semi - Supervised
  4. Reinforcement learning
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

How do you define machine learning

A

modern software development technique that enables computers to solve problems by using examples of real world data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is the difference between a model parameter and a hyperparameter

A

Parameters are set and changed while hyperparameters are parameters of the algorithm itself, not of the model and cannot be changed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

How would you define action

A

For every state, an agent needs to take an action toward achieving its goal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

How would you define agent

A

The piece of software you are training is called an agent. It makes decisions in an environment to reach a goal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

How would you define discriminator

A

A neural network trained to differentiate between real and synthetic (fake) data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

How would yo define discriminator loss

A

Evaluates how well the discriminator differentiates between real and fake data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

How would you define edit event

A

When a note is either added or removed from your input track during inference

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

How would you define environment

A

The environment is the surrounding area within which the agent interacts

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Describe exploration vs. exploitation

A

An agent should exploit known information from previous experiences to achieve higher cumulative rewards, but it also needs to explore to gain new experiences that can be used in choosing the best actions in the future.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

How would you define generator

A

A neural network that learns to create new data resembling the source data on which it was trained

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How would you define generator loss

A

Measures how far the output data deviates from the real data present in the training dataset

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

How would you define hidden layer

A

A layer that occurs between the output and input layers. Hidden layers are tailored to a specific task.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

How would you define input layer

A

The first layer in a neural network. This layer receives all data that passes through the neural network

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

How would you define output layer

A

The last layer in a neural network. This layer is where the predictions are generated based on the information captured in the hidden layers

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

How would you define piano roll

A

A two dimensional piano roll matrix that represents input tracks.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

In a piano roll, how are time and pitch resented

A

Time is on the horizontal axis, and pitch is on the vertical axis

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

How would you define reward

A

Feedback is given to an agent for each actions it takes in a given state (as a numerical reward)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What is the AWS machine learning mission

A

To put machine learning in the hands of every developer

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

What is Amazon SageMaker

A

A fully managed service that removes complexity from machine learning workflows so every developer and data scientist can deploy machine learning for a wide range of use cases

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

What can you accomplish by using AWS pre-trained AI services

A

You can apply ready-made intelligence to a wide range of applications such as personalized recommendations, modernizing contact center, improving safety and security, and increasing customer engagement

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

How would you define AWS DeepLens

A

A deep learning enabled video camera that allows you to deploy trained models directly to the device

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

What are four key components required for an WS DeepLens based project

A
  1. Collect your data and store it in an Amazon S3 bucket
  2. Train your model using jupiter notebook in SageMaker
  3. Deploy your model using AWS Lambda to deploy the trained model to your AWS DeepLens device
  4. View model output using Amazon IoT Greenrass after it is deployed
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

How would you define DeepRacer

A

An autonomous race ca designed to test reinforcement learning models by racing on a physical track

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

How would you define AWS DeepComposer

A

A composing device powered by generative AI that creates a melody that transforms into a complexity original song

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

What are the three main components of neural networks

A
  1. Input layer
  2. Hidden layer
  3. Output layer
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

How would you define image classification

A

The most common application of computer vision in use today. It can be used to answer questions like “whats in this image?” This type of task has application in text detection or optical character recognition (OR) and content

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

How would you define object detection

A

Closely related to image classification, but allows users to gather more granular detail about an image.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

How would you define semantic segmentation

A

Another common application of computer vision that takes a pixel approach. Instead of just identifying whether an object is present or not, it tries to identify, down to the pixel level, which part of the image is part of the object

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

How would you identify activity recognition

A

An application of computer vision that is based around videos rather than just image. Video has the added dimension of time and, therefore, models are able to detect changes that occur over time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

In reinforcement learning, what is an agent trained to do

A

Achieve a goal based on the feedback it receives as it interacts with an environment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
36
Q

In reinforcement learning, what does the agent collect

A

A number as a reward for each action it takes

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
37
Q

In reinforcement learning, what are the actions that help the agent achieve its goal incentivized with

A

Higher numbers

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
38
Q

In reinforcement learning, what do unhelpful actions result in

A

A low reward or no reward

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
39
Q

In reinforcement learning what does the agent learn over time (through trial and error)

A

To map gainful actions to situations

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
40
Q

What is reinforcement learning particularly useful for

A

Addressing sequential problems with long term goals

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
41
Q

Name four real-world examples of reinforcement learning

A
  1. Industrial robotics
  2. Fraud detection
  3. Stock trading
  4. autonomous driving
42
Q

How would you define state

A

Defined by the current position within the environment that is visible, or known, to the agent

43
Q

How would you define episode

A

Represents a period of trial and error when an agent makes decisions and gets feedback from its environment

44
Q

How would you define algorithm

A

A set of instructions that tells a computer what to do

45
Q

How would you define a soft actor critic (SAC)

A

Embraces exploration and is data - efficient, but can lack stability

46
Q

How would you define a proximal policy optimization (PPO)

A

Stale but data hungry

47
Q

How would you define an action space

A

The set of all valid actions, or choices, available to an agent as it interacts with an environment

48
Q

How would you define a discrete action space

A

Represents all of an agents possible actions for each state in a finite set of steering angle and throttle combinations

49
Q

How would you define a continuous action space

A

Allows the agent to select an action from a range of values that you define for each state

50
Q

How would you define learning rate

A

A hyperparameter that controls how many new experiences are counted in learning at each step

51
Q

What does a higher learning rate result in

A

Faster training, but may reduce the model’s quality

52
Q

What is the purpose of the reward function

A

To encourage the agent to reach its goal

53
Q

How does the reward function achieve its goal

A

Each stat on the grid is assigned a score, you incentivize behavior that supports your goal

54
Q

In reinforcement learning, what is one of your most important jobs

A

Figuring out how to reward which actions

55
Q

How would you define reward function

A

The actual code you write to elf your agent determine if the action it just took was good or bad, and how good or bad it was

56
Q

How would you define exploration

A

The more training an agent gets, the more it leans about an environment. This experience helps it become more confident about the actions it chooses. An agent needs to explore to gain new experiences that can be used in choosing the best actions in the future

57
Q

How would you define exploitation

A

Using information from previous experiences to help it reach its goal. An agent should exploit known information from previous experiences to acheieve higher cumulative rewards

58
Q

How would you define a reward graph

A

Where the DeepRacer metrics are displayed

59
Q

What does plotting the total reward from each episode allow you to see in a reward graph

A

how the model performs over time. The higher the reward, the better the model performs

60
Q

How does a balance of exploration and exploitation help a reinforcement learning model

A

The more an agent learns about its environment the more confident it becomes about the actions it chooses. If an agent doesn’t explore enough, it often sticks to information its already learned even if this knowledge doesn’t help the agent achieves it goal. The agent can use information from previous experiences to help it make future decisions that enable it to reach its goal .

61
Q

In a reward graph, what is represented in the average reward

A

The average reward the agent earns during training iteration

62
Q

IN a reward graph - how is the average in the average reward calculated

A

by averaging the reward earned across all episodes in the training iteration

63
Q

In a reward graph, what is represented in the average percentage completion (training)

A

The average percentage of the track completed by the agent in all episodes run during the evaluation period

64
Q

In a reward graph, what does the best model line allow you to see

A

Which of your model iterations had the highest average progress during the evaluation

65
Q

In a reward graph, in the best model line, what is a check point

A

A snapshot of a model that is captured after each training (policy-updating) iteration

66
Q

In a reward graph, what does the reward primary y - axis show

A

The reward earned during a training iteration

67
Q

In a reward graph, what does the percentage track complete ion secondary y - axis show

A

The percentage of the track the agent completed during a training iteration

68
Q

In a reward graph, what does the iteration x-axis show

A

The number of iterations completed during your training job

69
Q

In AWS DeepRacer, when does overfitting or overtraining become an issue

A

When a model is trained on a specific track for too long

70
Q

What should a good model be able to make decision based on

A

Features of the road, such as sidelines and center lines, and be able to drive on just about any track

71
Q

What does an over trained model learn to navigate

A

Landmarks specific to an individual track

72
Q

How would you define discriminative model

A

It aims to answer the question “if i’m looking at some data, how can i best classify this data or predict a value”

73
Q

How would you define generative model

A

It aims to answer the question “have i seen data like this before”

74
Q

What can the patterns learning in a generative model be used for

A

To create brand new examples of data which look similar to the data it saw before

75
Q

How would you define auto regressive convolutional neural networks (AR-CNNs)

A

Used to study systems that evolve over time an assume that the likelihood of some data depends only on what has happened in the pas.

76
Q

What are AR-CNNs useful for

A

As a way of looking at many systems, from weather prediction to stock prediction

77
Q

How would you define generative adversarial networks (GANs)

A

A machine learning model format that involves pitting two networks against each other to generate new content

78
Q

In a generative adversarial network, what does it swap back and forth between and why

A

A generator network (responsible for producing new data) and a discriminator network ( responsible for measuring how closely the generator networks data represents the training dataset)

79
Q

What are transformer based models most often used for

A

To study data with some sequential structure (such as the sequence of words in a sentence)

80
Q

What can you use for an input track in DeepComposer

A
  1. A sample track
  2. A recorded custom track
  3. Imported track
81
Q

In DeepComposer, what can you use for the machine learning technique

A

Either a sample model or a custom model

82
Q

What are the three supported generative AI techniques in DeepComposer

A
  1. Generative adversarial networks(GANs)
  2. Auto-regressive convolutional neural networks (AR-CNNs)
  3. Transformers
83
Q

In DeepComposer, what is the GAN technique used for

A

To create accompaniment tracks

84
Q

In DeepComposer, what is the AR-CNN technique used for

A

To modify the notes in your input track

85
Q

In DeepComposer, what is the transformers technique used for

A

To extend your input track by up to 30 seconds

86
Q

In a GAN, what are the two neural networks that are pit again each other

A
  1. a generator

2. a discriminator

87
Q

How would you define a generator

A

A neural network that learns to create new data resembling the source data on which it was trained

88
Q

How would you define discriminator

A

A neural network trained to differentiate between real and synthetic (fake) data

89
Q

What does the generator learn to do

A

Produce more and more realistic data

90
Q

What does the discriminator do

A

Iteratively gets better at learning to differentiate real data from the newly created data

91
Q

How would you define generator loss

A

Measures how far the output data deviates from the real data presenc in the training dataset, this feedback is then used by the generator to incrementally get better at create it realistic music

92
Q

How would you define discriminator loss

A

Evaluates how well the discriminator is differentiating between real and fake data

93
Q

How is time represented on each two dimensional piano roll

A

On the horizontal axis

94
Q

How is pitch represented on each two dimensional piano roll

A

On the vertical axis

95
Q

How would you define edit event

A

When a note is either added or removed from your input track during inference

96
Q

How would you define binary classifier

A

It classifies inputs into two groups - “real” and “fake”

97
Q

To detect both the cat and the dog present in an image, what kind of computer vision model would you use

A

Object detection

98
Q

Which computer vision based task would you use to detect that the dog in an image is sleeping

A

Image classification

99
Q

Which Computer vision based task would you use to detect the exact location of the car and the dog in an image

A

Semantic (instance) segmentation

100
Q

What kind of computer vision model would you use to count the number of cars in an image

A

Object detection

Introduction to Machine Learning (2 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions