WorksheetsClustering Techniques and Applications
Total questions: 8
Worksheet time: 4mins
Which of the following best describes unsupervised machine learning?
It uses labeled data to predict outcomes.
It creates categories or groups from unlabeled data.
It requires feedback on whether its predictions are correct.
It is primarily used for classification tasks with known categories.
What is the main purpose of clustering in data analysis?
To predict a specific numerical value.
To classify data into predefined categories.
To group similar data points together without prior labels.
To identify relationships between independent and dependent variables.
After selecting initial centroids in K-means clustering, what is the next step?
Recalculate the centroids based on the entire dataset.
Assign each data point to the closest centroid.
Determine the optimal number of clusters.
Plot the data points on a graph.
In clustering, what does a high silhouette score indicate?
The clusters are poorly defined and have significant overlap.
The data points within each cluster are close to each other, and clusters are well-separated.
The clustering algorithm failed to converge.
The number of clusters chosen is too high.
What is the initial step in hierarchical clustering when grouping a set of individual data points?
Combine all data points into a single large cluster.
Randomly assign data points to a predetermined number of clusters.
Treat each individual data point as its own separate cluster.
Identify the two most dissimilar data points and place them in separate clusters.
In a dendrogram, what does it indicate when two clusters join higher up on the graph?
The clusters are very similar to each other.
The clusters are less similar to each other.
The clusters contain an equal number of data points.
The clusters represent the final grouping of all data points.
How can hierarchical clustering be beneficial in understanding complex conditions like Autism Spectrum Disorder (ASD)?
It helps to simplify the diagnostic criteria for ASD.
It allows for the creation of subgroups of individuals with similar traits, leading to more targeted treatments.
It determines the exact cause of ASD in individual patients.
It replaces traditional diagnostic methods with a purely data-driven approach.
On a radar graph used to display developmental domain scores for clusters, what do scores closer to the center of the circle represent?
Higher proficiency in that developmental domain.
Lower proficiency in that developmental domain.
An average score across all developmental domains.
The most common score within the cluster.
