Google Machine Learning Flashcards

1
Q

AI

A

The ability of a digital computer to perform tasks that intelligent human beings perform

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

ML

A

Used by machines to make decisions based on data without getting specific instructions

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

Training Data

A

The data that creates the model for ML predictions

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

Model Training

A

The process of developing the a model for training data, with the goal of answering questions with the highest degree of accuracy

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

What are the seven steps of Machine Learning?

A

1) Gather the Data
2) Prepare the Data
3) Choose a Model
4) Training
5) Evaluation
6) Hyperparameter Training
7) Prediction

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Gathering Data

A

Ensure you haven’t collected too much of any particular kind of data, split data into training (80%) and evaluation (20%), you may need to normalize or deduplicate data

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

Choosing a Model

A

Ensure you a picking a model that is suitable to the data that you want to collect

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

Training

A

Use X + W * Y + b where W is weight and b is bias. These values are manipulated to determine if predictions are accurate.

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

Evaluation

A

Once training is complete, model is evaluating based off test data against training

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

Hyperparameter Tuning

A

Fine tune your assumed parameters or hyperparameters to get higher accuracy

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

Prediction

A

Use your model for evaluation of data

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

Supervised Learning

A

Most common model, used when the training data and validation data is labeled and the task is learning how to set a label to input data.

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

Classification

A

A subclass of supervised learning, occurs when output data is a category (ex. apple, pear, orange)

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

Regression

A

A subclass of supervised learning, occurs when the output data is a value, such as cost and temperature

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

Unsupervised Learning

A

When training data is not labeled and model attemps to learn the structure of the data and export information or features that might be useful for classification. Accuracy can’t be measure but data can be moved into groups.

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

Clustering

A

A subclass of unsupervised learning, occurs when you want to group the data

17
Q

Association

A

A subclass of unsupervised learning, occurs when you want to link two different actions or behaviors

18
Q

Semi-Supported Machine Learning

A

When part of the data is labelled but part of it isn’t resulting in a mix of both methods

19
Q

TensorFlow

A

For Data Scientists. An option for those who want to work with ML from scratch, and is a software library that is developed and maintained by Google.

20
Q

ML Engine

A

For Data Scientists. An option for those who want to train their own models, but use Google for training and predicitions. Managed TensorFlow service that offloads all infrastructure and software bits from users. Integrates with other GCP services.

21
Q

Pretrained ML Models

A

For Developers. An option for those who want to leverage ML without having knowledge of it. Uses Google Developed models to perform predictions.

22
Q

Auto ML

A

For Developers. An option for those who want to leverage ML without having any knowledge or it and where the pretrained models are not for a fit purpose. Allows models to be trained by supporting labelled data.

23
Q

Cloud Tensor Processing Units (TPUs)

A

Google custom developed application specific integrated circuts (ASICs) used to speed up ML workloads. Enhance linear algebra computation for use in models using matrix computations, without custom TensorFlow operations inside the main traning loop, that take a long time to train, or have very large batch sizes.

24
Q

Cloud Speech to Text API

A

Empowers developers with the ability to turn speech into text, API accepts audio and returns text transcription

25
Q

Cloud Text to Speech API

A

Gives developers the ability to transform text into a form of Synthesis Markup Language (SSML) input into audio data of natural human speech

26
Q

Cloud Translation API

A

Enables translation into thousands of languages, and detect language if it is unknown. Can be used directly in code with REST API.

27
Q

Cloud Natural Language API

A

Allows leverage of deep learning models that Google uses for it’s search engine to analyze text and Google Assistant (extract information on entities, categorize entities, perform sentiment analysis, and perform syntax analysis)

28
Q

Cloud Vision API

A

Provides vision detection features such as Image Labeling, face and landmark detection, optical character recognition (OCR) and tagging explicit content

29
Q

Cloud Video Intelligence

A

Allows you to analyze video that’s been uploaded to Cloud Storage, using labels, shots, and tagging explicit content

30
Q

DialogFlow

A

Tool outside of GCP (originates in api.ai) developed to perform human to computer interaction using natural language processing. Can produce auto ansers in skype, google assistant, slack and fb messenger.

31
Q

Auto ML Vision

A

Classifies your images according to your own defined labels

32
Q

Auto ML Translation

A

Performs translation queries, returns specific results to your domain

33
Q

Auto ML Natural Language

A

Classifies English language content into a custom set of categories

34
Q

Auto ML Tables

A

Turns structured data into predictive insights

35
Q

Auto ML Video Intelligence

A

Classifies segments of videos