Brainscape's Knowledge GenomeTM

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


See full index

Data Science > From Questions > Flashcards

From Questions Flashcards

You may prefer our related Brainscape-certified flashcards:
Biology 101 flashcards
1
Q

What is CRISP-DM?

A

Cross Industry standard process for data mining - data mining process model. It consists six phases:
1. Business understanding
2. Data understanding
3. Data preparation
4. Modeling
5. Evaluation (validate your results)
6.deployment (put the model into production)

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

Is CRISP-DM iterative process?

A

Yes due to continues process cycle and each step is important.

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

What are preattentive attributes? examples

A

Help us to create visuals that emphasise the most important information

First thing you see in the data

Examples - color form size form

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

Gestalt principles of visual perception

A

It has 6 principles:
1. Proximity ( element close to each other perceived as a group)
2. Similarity (visually similar color size)
3. Closure ( information filling with general i formation)
4. Continuity (the eye is drawn to continues lines and paterns)
5. Enclosure (elements not close to each other perceived as a group)
6. Connection (physically connected as a group)

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

What is MLE? And its purpose?

A

MAXIMUM LIKEHOOD ESTIMATION
Method that estimates the best parameters to probabilistic model.

Its purpose to make observation most probable under the given model

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

Properties that make MLE good?

A

1) consistency
2) asymptotic normality (normal distribution allows to do hypothesis test)
3) efficiency (makes the most precise estimates of the parameters)
4) invariance ( simplifies the estimation of transform parameters)

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

What method among supervised learning methods uses MLE?

A

Logistic regression, to estimate its parameters allowing it to effectively model the probability of binary outcomes.

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

Which learning framework linear regression belongs to

A

Supervised learning framework

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

Which learning framework Logistic regression belongs to

A

Supervised learning framework

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

Which data science task Linear regression solves ?

A

It is used to solve the regression tasks in data science to predict continues outcome variable .

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

Linear regression assumptions that it makes on the data:

A

1) Linearity ( relationship between dependent and independent variables)
2) Independence (observations are independent of each other
3) Homoscedasty (residuals have constant variance of independent variables )
4) normality (residuals are normally distributed )
5) No multicollinearity (variables are not highly correlated)
6) No autocorrelation (residuals are not correlated)

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

How to use linear regression model?

A

Y is the only one dependent variable
Also there is intercept ( constant ) variable
X is more independent variables

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

How to fit linear regression model?

A

Using least squares method

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

How predictions are made in linear regression model?

A

Predictions are made by applying the fitted linear equation to new data points.

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

What learning framework logistic regression model belongs to?

A

Supervised learning framework

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

Which data science task logistic regression model solves?

A

It predict the output with the given data

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

Assumptions that logistic regression model makes on the data?

A
  1. Binary dependant variable (have two outcomes 0 and 1)
  2. Linearity (relationship between independent and log odds of the dependent variables )
  3. Independence (observations is independent of each other)
  4. Absence of multicollinearity (independent variables are highly correlated)
  5. Sufficient sample size (sample size should be large enough to provide sufficient data point)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

How logistic regression model is used and how it works?

A

Variables of logistic regresiion are used to predict binary outcome (1 or 0, true or false)
This model is based on logistic function to make predicted values to probabilities

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

How to fit logistic regression model?

A

Involve estimating the coefficients

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

How predictions are made in logistic regression model?

A

It is made based on The logistic function which linear combination turns into probability

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

What is gradient decent? And how it works?

A

gradient decent is an iterative optimisation method that iteratively adjusts parameters to minimise a given function

22
Q

What are the methods to minimise function ( in gradient decent method)

A
  1. Scalar
  2. Multivariable
23
Q

Describe gradient decent method in the scalar case and in multivariable case?

A
  1. Scalar case - goal is to find the value of the only one variable X that minimises function f(x)
  2. Multivariable case - the goal is to find vector that minimises function f(x)
24
Q

How to make gradient decent more effective ?

A

Use adaptive methods such as AdaGrad or Adam or use mini-batch gradient decent.

25
Q

How we evaluate the quality of a logistic regression model, referring to possible performance indicators?

A
  1. u need to find right threshold to make class labels
  2. Do a confusion matrix
  3. After that you can evaluate accuracy and error rate
26
Q

What confusion matrix describes

A

How many predictions were correct and incorrect

27
Q

How the threshold affects the performance indicators and how we choose its value?

A

By changing the threshold we get different confusion matrixes. Default threshold 0,5 it maximises the accuracy but depending on your data you can lover it or increase threshold and it modifies accuracy, error rate and all confusion matrix components

28
Q

How to evaluate the quality of a linear regression model, referring to possible performance indicators ?

A
  1. Residuals sum of squares (RSS)
  2. Root mean squared error (rmse)
  3. Mean squared error (MSE)
  4. No threshold
29
Q

What is approximation trade off that is cone ted to supervised learning methods?

A

Is about finding the right balance between making your model simple enough to work well on new data and complex enough to fit in the training data

30
Q

How does the selection of the hypothesis space H of a supervised learning method affect the the trade off?

A

If the hypothesis space is to simple the model might miss important information patterns (high bias, under fitting)
If its to complex the model might fit the noise in the training data to closely (high variance, overfitting)
The key is to find middle ground where the model captures the right trends without getting distracted by irrelevant details.

31
Q

What are the differnces between regression trees and classification trees?

A

Regresion trees - for predicting continues numeric outcomes

Classification trees - predicts caregorical outcomes

32
Q

Decision tree types

A

Regression and classification

33
Q

Recursive binary splitting in regression trees

A

Minimise variance

34
Q

Cost-complexity pruning in decision trees

A

Both trees purpose is to remove the tree by removing less important splits

Regression trees - removing splits that don’t significantly reduce the overall variance

Classification trees - remove splits that don’t significantly improve the purity of the groups

35
Q

Making predictions decision trees

A

Regression - predict the average value of the target variable
Classification - predicts the most common category

36
Q

What are forward propagation

A

Is the process by which the inputs data passes thou the neural network to generate outcome

37
Q

What is back propagation

A

Is the process in neural networks of adjusting the weight and biases to minimise the error in predictions

38
Q

Advantages of back propagation?

A

Efficient
Less tine consuming when its done by programs
Flexibility
Generalisation

39
Q

What is Computer vision and how does it relate to machine vision ?

A

Computer vision helps computers understand and interpret data like images and videos.

Machine vision applies computer vision technologies specifically to industrial processes

40
Q

Which tasks Computer vision solve?

A
  1. Image classification
  2. Object detection
  3. Segmentation
  4. Annotation
41
Q

Challenge that drove computer vision development?

A

Challenge: the need to achieve higher accuracy as efficiency in image recognition tasks

42
Q

Standard de facto methods used to address Computer vision tasks?

A

CNN

43
Q

What is the purpose if transfer learning?

A

Purpose : is to leverage a pre-trained data model which has already learned features from a large dataset and applies to a new task

44
Q

How transfer learning compares to traditional machine learning?

A

Machine learning generates a new model for every new task while transfer learning uses already generated model for new tasks

45
Q

How can we apply transfer learning and what are you its advantages?

A

Using transfer learning on CNN saves time and is more efficient in terms of saving data

46
Q

Based on two basic paradigms describe hierarchical clustering method?

A

• Agglomerative - button up approach, each observation represents a cluster

• Divisive - top down approach, we have only one big cluster which contains all the data

47
Q

Based on the concept of linkage describe hierarchical clustering method?

A
  1. Complete linkage
  2. Single linkage
  3. Average linkage
  4. Centroid linkage
48
Q

What is dendrogram

A

Diagram of clusters

49
Q

How do we select the number of clusters

A

Number is selected by vertical lines

50
Q

Describe the two interpretations of Principal Component Analysis (PCA)

A
  1. Data reduction ( reduces the number of features while keeping the most importantant info)
  2. Pattern recognition (identifies patterns where the data varies the most )
51
Q

Which matrix decomposition PCA rely on and how?

A

Relies on eigenvalue decomposition Singular value decomposition

  1. Breaks down original data matrix
  2. Identify the principal components
  3. These components

Data Science (1 decks)

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