Final Review for CSIT 357: Artificial Intelligence

These flashcards cover key terms and concepts from the lecture notes on Artificial Intelligence, focusing on neural networks, machine learning, and natural language processing.

Which type of data is structured and has a predefined format?

Structured data.

What is unstructured data?

Data without a fixed format, like images, videos, or social media posts.

Define semi-structured data.

Partly organized data such as JSON or XML files.

What are Labeled Data used for?

Supervised Learning.

What is the key difference between supervised and unsupervised learning?

Supervised learning uses labeled data, while unsupervised learning does not.

List one limitation of supervised learning.

Requires large labeled datasets that are expensive and time-consuming to prepare.

What is a characteristic of Nominal data?

Categories without any inherent order.

What are the four types of data in machine learning?

Nominal, Ordinal, Discrete, Continuous.

What does a Convolutional Neural Network (CNN) mainly do?

Extract features from input data, typically images.

What does the ReLU activation function do?

Keeps positive values and sets negative ones to zero.

What are the phases of Natural Language Processing (NLP)?

Lexical Analysis, Syntactic Analysis, Semantic Analysis, Discourse Integration, Pragmatic Analysis.

Name one method used in the NLP process for breaking down text into words.

Tokenizing.

What is the purpose of stemming in NLP?

To obtain the word stem of a word.

What does lemmatization achieve in NLP?

It identifies the base form of a word present in the dictionary.

In part of speech tagging, what do you explain to the algorithm?

The concept of nouns, verbs, and other parts of speech.

What is the main goal of computer vision in AI?

To enable computers to understand and interpret visual data.

How do computer vision and NLP interact?

Through processes like recognition, reconstruction, and reorganization.