Lecture 7 - BI and Data Mining 2

Question 1

Overfitting results in?

Answer 1

Decision trees that are more complex than necessary

Question 2

Training error no longer provides?

Answer 2

A good estimate of how well the tree will perform on previously unseen records

Question 3

What can cross validation technique be used for?

Answer 3

Cross validation technique can be used to compare the performance of different machine learning models on the same data set

Question 4

What is leave-one-out?

Answer 4

Similar to k-fold where k=number of samples

Question 5

What is bootstrapping?

Answer 5

Random sampling with replacement

Question 6

Describe bootstrap method?

Answer 6

Refers to random sampling with replacement.

Question 7

What is Neural Networks?

Answer 7

An artificial network consists of a pool of simple processing units which communicate by sending signals to each other over a large number of weighted connections.

Question 8

What is a test stage in NN?

Answer 8

Each unit performs a relatively simple job:
receive input from neighbors or external sources and use this to compute an output signal which is propagated to other units

Question 9

What is the learning stage in NN?

Answer 9

A task of the adjustment of the weights

Question 10

What is feed-forward networks?

Answer 10

Where the data flow from input to output units is strictly feed-forward.
The data processing can extend over multiple layers of units, but no feedback connections or connections between the units of the same layer are present.

Question 11

Perceptron?

Answer 11

A single layer feed-forward network consists of one or more output neurons, each of which is connected with a weighted factor w to all of inputs x

Question 12

How does learning in Perceptrons work?

Answer 12

The weights of the neural networks are modified during the learning phase

Question 13

Convergence Theory?

Answer 13

If there exists a set of connection weights w* which is able to perform the transformation y=d(x) the perceptron learning rule will converge to some solution in a finite number of steps for any initial choice of the weights

Question 14

What is Backpropagation?

Answer 14

The multi-layer networks with a linear activation can classify only linear separable inputs or, in case of function approximation, only linear functions can be represented.

Question 15

What is SVM?

Answer 15

Support Vector Machine

Question 16

Properties of SVM?

Answer 16

Flexibility in choosing a similarity function
Sparseness of solution when dealing with large data sets
Ability to handle large feature spaces
Overfitting can be controlled by soft margin approach

Question 17

SVM applications?

Answer 17

Text categorization
Image classification
Bioinformatics
Hand-written character recognition

Question 18

Machine learning focuses on?

Answer 18

Prediction, based on known properties learned from the training data

Question 19

Data mining focuses on?

Answer 19

The discovery of previously known properties in the data. This is the analysis step of Knowledge Discovery in Databases

Question 20

Data mining uses many?

Answer 20

Machine learning methods but often with a slightly different goal in mind

Question 21

Machine learning also employs?

Answer 21

Data mining methods as unsupervised learning or as preprocessing step to improve learner accuracy

Question 22

What is Cluster Analysis used for in Data Mining?

Answer 22

Used for automatic identification of natural groupings of things
Employ unsupervised learning
Learns the clusters of things from past data, then assigns new instances
There is not an output/target variable

Question 23

What is k-Means clustering alrgorithm?

Answer 23

K: pre-determined number of clusters

Algorithm Step 0 determine the value of K

Question 24

Steps of k-means?

Answer 24

Step 1: Randomly generate k random points as initial cluster centers
Step 2: Assign each points to the nearest cluster center
Step 3: Re-compute the new cluster centers

Question 25

What is k-means repetition step?

Answer 25

Repeat steps 3 and 4 until some convergence criterion is met

Question 26

What is cluster analysis?

Answer 26

Finding groups of objects such that the objects in a group will be similar to one another and different from the objects in the other groups

Question 27

Applications of Cluster Analysis?

Answer 27

Understanding
- Group related documents for browsing, group genes, and proteins that have similar functionality

Summarization
- reduce the size of large data sets

Question 28

What is a clustering?

Answer 28

A set of clusters

Question 29

What are the types of Clusterings?

Answer 29

Partitional Clustering

Hierarchical Clustering

Question 30

What is Partitional Clustering?

Answer 30

A division data objects into non-overlapping subsets such that each data object is in exactly one subset

Question 31

What is Hierarchical Clustering?

Answer 31

A set of nested clusters organized as hierarchical tree

Question 32

What is Association Rule?

Answer 32

Is a rule-based machine learning method for discovering interesting relations between variables in large databases

Question 33

Challenges of Frequent Itemset mining?

Answer 33

Multiple scans of transaction database
Huge number of candidates
Tedious workload of support counting for candidates