Machine learning Quiz # 7

Compared to the variance of the Maximum Likelihood Estimate (MLE), the variance of the Maximum A Posteriori (MAP) estimate is ___

Higher

Same

Lower

It could be any of the above

___ refers to a model that can neither model the training data nor generalize to new data.

Good fitting

Overfitting

Underfitting

All of the above

What does it mean to underfit your data model?

There is too little data in your training set.

There is too much data in your training set.

There is not a lot of variance but there is a high bias.

Your model has low bias but high variance.

Asian user complains that your company's facial recognition model does not properly identify their facial expressions. What should you do?

Include Asian faces in your test data and retrain your model.

Retrain your model with updated hyperparameter values.

Retrain your model with smaller batch sizes.

Include Asian faces in your training data and retrain your model.

You work for a website that helps match people up for lunch dates. The website boasts that it uses more than 500 predictors to find customers the perfect date, but many costumers complain that they get very few matches. What is a likely problem with your model?

Your training set is too large.

You are underfitting the model to the data.

You are overfitting the model to the data.

Your machine is creating inaccurate clusters.

(Mostly) whenever we see kernel visualizations online (or some other reference) we are actually seeing:

What kernels extract

Feature Maps

How kernels Look

The activations for class A, B and C before softmax were 10,8 and 3. The different in softmax values for class A and class B would be :

76%

88%

12%

0.0008%

The new dataset you have just scraped seems to exhibit lots of missing values. What action will help you minimizing that problem?

Wise fill-in of controlled random values

Replace missing values with averaging across all samples

Remove defective samples

Imputation

Which of the following methods can use either as an unsupervised learning or as a dimensionality reduction technique?

SVM

PCA

LDA

TSNE

What is the main motivation for using activation functions in ANN?

Capturing complex non-linear patterns

Transforming continuous values into

Help avoiding the vanishing/exploding gradient problem

Their ability to activate each neurons individually.

Which loss function would fit best in a categorical (discrete) supervised learning ?

Kullback-leibler (KL) loss

Binary Crossentropy

Mean Squared Error (MSE)

Any L2 loss

You create a decision tree to show whether someone decides to go to the beach. There are three factors in this decision: rainy, overcast, and sunny. What are these three factors called?

Tree nodes

Predictors

Root nodes

Deciders

You need to quickly label thousands of images to train a model. What should you do?

Set up a cluster of machines to label the images

Create a subset of the images and label then yourself

Use naive Bayes to automatically generate labels.

Hire people to manually label the images

You need to select a machine learning process to run a distributed neural network on a mobile application. Which would you choose?

Scikit-learn

PyTorch

Tensowflow Lite

Tensorflow

Which choice is the best example of labeled data?

A spreadsheet

20,000 recorded voicemail messages

100,000 images of automobiles

Hundreds of gigabytes of audio files

In statistics, what is defined as the probability of a hypothesis test of finding an effect - if there is an effect to be found?

Confidence

Alpha

Power

Significance

You want to create a machine learning algorithm to identify food recipes on the web. To do this, you create an algorithm that looks at different conditional probabilities. So if the post includes the word flour, it has a slightly stronger probability of being a recipe. If it contains both flour and sugar, it even more likely a recipe. What type of algorithm are you using?

Naive Bayes classifier

K-nearest neighbor

Multiclass classification

Decision tree

What is lazy learning?

When the machine learning algorithms do most of the programming

When you don't do any data scrubbing

When the learning happens continuously

When you run your computation in one big instance at the beginning

What is Q-learning reinforcement learning?

Supervised machine learning with rewards

A type of unsupervised learning that relies heavily on a well-established model

A type of reinforcement learning where accuracy degrades over time

A type of reinforcement learning that focuses on rewards

The data in your model has low bias and low variance. How would you expect the data points to be grouped together on the diagram?

They would be grouped tightly together in the predicted outcome.

They would be grouped tightly together but far from the predicted.

They would be scattered around the predict outcome.

They would be scattered far away from the predicted outcome.

Your machine learning system is using labeled examples to try to predict future data, compare that data to the predicted result, and then the model. What is the best description of this machine learning method?

Unsupervised learning

Semi-supervised learning

Supervised learning

Semi-reinforcement learning

In the 1983 movie WarGames, the computer learns how to master the game of chess by playing against itself. What machine learning method was the computer using?

Binary learning

Supervised learning

Unsupervised learning

Reinforcement learning

You are working with your machine learning algorithm on something called class predictor probability. What algorithm are you most likely using?

Multiclass binary classification

Naive Bayes

Unsupervised classification

Decision tree analysis

What is one of the most effective way to correct for underfitting your model to the data?

Create training clusters

Remove predictors

Use reinforcement learning

Add more predictors

Your data science team is often criticized for creating reports that are boring or too obvious. What could you do to help improve the team?

Suggest that the team is probably underfitting the model to the data.

Suggest that unsupervised learning will lead to more interesting results.

Make sure that they are picking the correct machine learning algorithms.

Encourage the team to ask more interesting questions.

What is the difference between unstructured and structured data?

Unstructured data is always text.

Unstructured data is much easier to store.

Structured data has clearly defined data types.

Sturctured data is much more popular.

You work for a startup that is trying to develop a software tool that will scan the internet for pictures of people using specific tools. The chief executive is very interested in using machine learning algorithms. What would you recommend as the best place to start?

Using an unsupervised machine learning algorithm to cluster together all the photographs.

Crate a data lake with an unsupervised machine learning algorithm.

Use a combination of unsupervised and supervised machine learning to create machine-defined data clusters.

Use supervised machine learning to classify photographs based on a predetermined training set.

In supervised machine learning, data scientist often have the challenge of balancing between underfitting or overfitting their data model. They often have to adjust the training set to make better predictions. What is this balance called?

The under/over challenge

Balance between clustering classification

Bias-variance trade-off

The multiclass training set challenge

What is conditional probability?

The probability that doing one thing has an impact on another thing

The probability that certain conditions are met

The probability that, based on certain conditions, something will always be incorrect

The probability of something being the correct answer

K-means clustering is what type of machine learning algorithm?

Reinforcement

Supervised

Unsupervised

Classification

Quiz:	Machine learning Quiz # 7
Subject:	Basic Machine Learning
Total Questions:	215 MCQs
Time:	215 Minutes