OS1 Day 7 Exploring AI Concepts and Applications

Front

What is the primary goal of supervised machine learning?

Back

To predict outcomes based on labeled data

Answer explanation

The primary goal of supervised machine learning is to predict outcomes based on labeled data. This involves training a model on input-output pairs to make accurate predictions on new, unseen data.

Front

Which of the following is a common ethical concern in AI? High computational cost, Data privacy and security, Lack of scalability, Limited data storage

Back

Data privacy and security

Answer explanation

Data privacy and security is a major ethical concern in AI, as it involves protecting sensitive information from unauthorized access and ensuring that data is used responsibly.

Front

In Natural Language Processing, what does the term "tokenization" refer to?

Back

Splitting text into individual words or phrases

Answer explanation

Tokenization is the process of splitting text into individual words or phrases, which is essential for various NLP tasks. This makes 'Splitting text into individual words or phrases' the correct choice.

Front

Which of the following is a common task in computer vision? Speech recognition, Image classification, Text summarization, Sentiment analysis

Back

Image classification

Answer explanation

Image classification is a key task in computer vision, where algorithms are trained to identify and categorize images. The other options, like speech recognition and sentiment analysis, are related to different fields such as audio processing and natural language processing.

Front

What is a feature of a common AI workload?

Back

Large data throughput

Answer explanation

A common AI workload typically involves processing large volumes of data, which requires large data throughput to handle the input and output efficiently. High latency, low computational power, and minimal data storage are not characteristic features.

Front

Which algorithm is typically used for classification tasks in machine learning? Options: K-Means, Decision Trees, Principal Component Analysis, Apriori

Back

Decision Trees

Answer explanation

Decision Trees are commonly used for classification tasks as they create a model based on decision rules derived from the data. In contrast, K-Means is for clustering, PCA for dimensionality reduction, and Apriori for association rule learning.

Front

What is the purpose of a confusion matrix in machine learning?

Back

To visualize the performance of a classification model

Answer explanation

A confusion matrix is used to visualize the performance of a classification model by showing the true vs. predicted classifications, helping to identify errors and understand model accuracy.

Front

Which of the following is an example of AI bias? A model that performs equally well across all demographics, A model that favors one demographic over others, A model that has high accuracy, A model that uses a large dataset

Back

A model that favors one demographic over others

Answer explanation

AI bias occurs when a model favors one demographic over others, leading to unequal performance. The correct choice highlights this issue, while the other options indicate fairness or performance without bias.

Front

In Natural Language Processing, what is "stemming"?

Back

Reducing words to their root form

Answer explanation

Stemming is the process of reducing words to their root form, which helps in normalizing variations of a word for better text analysis. For example, 'running' becomes 'run'. This distinguishes it from other options like stop word removal.

Front

What is the primary function of convolutional layers in a Convolutional Neural Network (CNN)?

Back

To detect and learn spatial hierarchies in images

Answer explanation

The primary function of convolutional layers in a CNN is to detect and learn spatial hierarchies in images. They achieve this by applying filters that capture patterns and features at various levels of abstraction.