IS 4490 - Unsupervised Learning, Reinforcement Learning, and Model Types

What is the key characteristic that distinguishes unsupervised learning from supervised learning?

Unsupervised learning works with unlabeled data without predefined target values

In K-means clustering, what does the 'K' represent?

The user-defined number of clusters

What is the primary goal of clustering?

To group similar data points together based on their characteristics

In association rule learning, what does "confidence" refer to?

The probability of one item being bought given that another item is bought

In reinforcement learning, how does an agent learn to make decisions?

By interacting with an environment and receiving rewards or penalties

Which characteristic is NOT typical of shallow machine learning models?

Use multiple layers of neural networks

Why are shallow ML models often preferred for structured data?

They are more interpretable, efficient, and can work well with smaller datasets

Which type of deep learning model is primarily used for image and video processing tasks?

Convolutional Neural Networks (CNNs)

Which deep learning models are designed to work with sequential data like text?

RNNs and LSTMs

Which of the following is NOT mentioned as a common NLP task?

Image segmentation

What is a key characteristic of unsupervised learning?

It works with unlabeled data to find patterns or structures.

What is the purpose of Dimensionality Reduction?

To reduce the number of features while preserving essential information.

Which of the following is a key characteristic of shallow machine learning models?

They generally require manual feature extraction and can perform well with smaller datasets.