Artificial Intelligence Question Bank - Class 10

The AI Project Cycle involves several stages: Problem Scoping, where you define the problem; Data Acquisition, where you gather information; Data Exploration, where you analyze your data; Modeling, where you build your AI model; and Evaluation, where you assess the model's performance.

The "4Ws" are Who, What, Where, and Why. By asking these questions, you can clearly define your problem and understand the context of your AI project.

A testing dataset is a separate set of data used to evaluate the performance of a trained AI model. It's like testing a student on a different set of questions to see if they've learned the material.

Supervised learning uses labeled data to train the model, like teaching a child through examples. Unsupervised learning explores unlabeled data to find patterns, like discovering new constellations in the night sky. Reinforcement learning involves training a model through trial and error, like a robot learning to walk.

The evaluation stage aims to assess the model's accuracy in predicting outcomes. It's like checking if a student understands the concept after learning it.

The analogy of an Artificial Neural Network (ANN) can be compared to parallel processing. This means that the ANN can process multiple tasks simultaneously, much like our brains.

System hacking is not an authentic source for data acquisition. It involves getting data illegally and potentially harming systems. The other options are reliable and ethical.

Linear graphs are best for visualizing continuous data, like exam scores, as they show trends and changes smoothly over time.

This approach involves using a set of rules or instructions defined by a developer to guide the AI's behavior. The AI then performs its tasks based on these pre-defined rules.

This approach allows the AI to learn from data without explicit rules. The AI is fed data and identifies patterns and trends on its own.

It helps define the problem clearly, outlining its scope, relevance, and impact. It answers questions like 'what problem are we solving?', 'where does it occur?', 'who is affected?', and 'why is it important?'

This goal aims to reduce poverty in all its forms globally by 2030. It includes targets like reducing extreme poverty, promoting sustainable economic growth, and ensuring social protection.

This goal aims to ensure inclusive and equitable quality education for all by 2030. It includes targets like providing free and compulsory primary and secondary education, increasing access to affordable and quality tertiary education, and promoting lifelong learning opportunities.

Data features define the kind of data needed for an AI project. It refers to the characteristics, properties, or attributes of the data that are relevant to the problem being solved.

This step involves evaluating the performance and effectiveness of the AI model. This is essential to understand its limitations and areas for improvement.

This model attempts to categorize data into specific groups based on their characteristics. It works by identifying features or patterns in data and assigning labels to them, which are then used to predict labels for new data.

A type of machine learning model that uses continuous data to predict an output based on patterns. For example, predicting salary based on previous salaries, increments, etc.

An unsupervised learning algorithm that groups similar data points together based on patterns and trends. It can identify known and unknown patterns.

The stage in the AI project cycle where you analyze and make sense of the collected data. You check if the data meets the project requirements and is free of errors.

A type of AI system inspired by the human brain and nervous system. It learns by adjusting the connections between artificial neurons.

An important feature of Artificial Neural Networks. It means the network can automatically identify important patterns in the data without explicit programming.

Each node in a neural network represents a simple machine learning algorithm, contributing to the overall learning process.

An AI project cycle is a structured method for planning, organizing, and managing AI development, ensuring effective execution and achieving defined goals.

Problem Scoping involves defining the problem you want to solve with AI, including identifying the target audience and the goals to be achieved.

Data Acquisition involves gathering the necessary information to train your AI model. It's crucial to obtain relevant, accurate, and sufficient data.

Data Exploration involves analyzing the collected data to understand patterns, trends, and potential issues. This helps in preparing the data for model training.

Modeling involves building the AI model based on the analyzed data. This stage involves choosing the appropriate algorithms and parameters to train the model.

Evaluation is the final stage where the performance of the trained model is assessed. This includes evaluating its accuracy, efficiency, and other relevant metrics.

Supervised learning involves training an AI model with labeled data, where each input is associated with a correct output. It's like teaching a child with examples and correct answers.

Unsupervised learning is a type of machine learning where the model learns from unlabeled data. The goal is to find patterns and relationships within the data, without any pre-defined categories or labels. Think of it like letting a child explore a room full of toys and discover their own categories based on shapes, colors, or textures.

Clustering algorithms are used to group data points into clusters based on similarity. Each cluster contains data points that are more similar to each other than to points in other clusters. Imagine grouping people into categories based on their hobbies, interests, or personality traits.

Classification algorithms are used to categorize data into predefined classes or categories. The model learns from labeled data to predict the class of new data points. Think of it like teaching a child different animal categories by showing them pictures of animals and labeling them as dogs, cats, birds, etc.

Regression algorithms are used to predict continuous outcomes, such as predicting house prices or weather forecasts. The model learns the relationship between input variables and the output variable, allowing it to predict values for new input data. Think of it as predicting the height of a sunflower based on the age of the plant.

Email spam detection is a classification problem because the model needs to categorize incoming emails as either spam or not spam, based on features like sender, subject, or content. The model learns from labeled data (spam and non-spam emails) to make these predictions.

Weather forecasting is a regression problem because the model needs to predict continuous values like temperature, humidity, and wind speed. The model learns from past weather data to predict future weather conditions.

The process of sorting data into groups or categories based on their characteristics. It's like putting toys into a box based on their type.

Finding a model that predicts a continuous value, not just categories. It's like finding a line that best fits all the data points.

A type of AI approach that uses pre-defined rules to guide its behavior. Think of it like a robot following a set of instructions.

An AI approach where the system learns from data without explicit rules. It's like a child learning by observing and experimenting.

A type of graph used to visualize continuous data, showing trends and changes smoothly. It's like drawing a line to show how something changes over time.