set-7

Answer: 3. Natural language understanding

Explanation:

• Natural Language Understanding (NLU) is a subfield of NLP that focuses on transforming human language into a format that machines can understand and process.
• It involves tasks like sentiment analysis, intent recognition, and entity extraction.

Answer: 3. Natural language understanding (NLU)

Explanation:

• Tasks like Automatic Ticket Routing, Machine Translation, and Question Answering are examples of Natural Language Understanding (NLU).
• These tasks require the machine to understand and interpret human language.

Answer: 4. Natural language generation

Explanation:

• Natural Language Generation (NLG) is the process of producing natural written or spoken language from structured or unstructured data.
• It is used in applications like chatbots, report generation, and voice assistants.

Answer: 4. Natural language generation

Explanation:

• Natural Language Generation (NLG) is used to generate responses for chatbots and voice assistants like Alexa, Google Assistant, and Siri.
• It converts structured data into human-like language.

Answer: 4. Natural language understanding and natural language generation

Explanation:

• Chatbots and “suggested text” features use both Natural Language Understanding (NLU) to interpret user input and Natural Language Generation (NLG) to produce responses.
• These technologies work together to enable seamless human-machine interaction.

Answer: 4. All of above

Explanation:

• Long-Short Term Memory (LSTM), Recurrent Neural Networks (RNN), and Markov chains are all models and methodologies used in Natural Language Generation (NLG).
• These models help in generating coherent and contextually relevant text.

Answer: 4. All of above

Explanation:

• NLP is challenging because imparting world knowledge to machines is complex.
• Fictitious words and poorly defined scopes add to the difficulty in understanding and generating human language.

Answer: 1. Opening Computer Browser

Explanation:

• Sentiment Analysis, Text Classification, and Chatbots are all applications of NLP.
• Opening a computer browser is a system-level task and is not related to NLP.

Answer: 2. Computer Vision

Explanation:

• Computer Vision is the field of AI that focuses on enabling computers to interpret and understand visual information from images or videos.
• It involves tasks like object detection, image recognition, and video analysis.

Answer: 2. Computer Vision

Explanation:

• Computer Vision uses machine learning models to classify objects in images.
• Applications like facial recognition for unlocking smartphones are examples of computer vision in action.

Answer: 2. Computer Vision

Explanation:

• The process described involves input sensing, interpretation, and output, which aligns with the workflow of Computer Vision.
• Computer Vision systems process visual data to produce meaningful outputs.

Answer: 2. Computer Vision

Explanation:

• Convolutional Neural Networks (CNNs) and Deep Learning are key technologies that drive Computer Vision.
• These technologies enable computers to analyze and interpret visual data effectively.

Answer: 3. Model-based vision

Explanation:

• Model-based vision is a computer vision technique that uses predefined templates or models to recognize objects in images.
• It compares the input image with stored templates to identify objects.

Answer: 1. Machine Vision / Computer Vision

Explanation:

• Machine Vision or Computer Vision involves using optical devices to capture and interpret images for information extraction or process control.
• It is widely used in automation and robotics.

Answer: 1. Robot

Explanation:

• A robot is a programmable machine designed to imitate human actions or appearance.
• Robots are used in various applications, from manufacturing to healthcare.

Answer: 1. Robot

Explanation:

• A robot must be able to gather information from its surroundings and physically interact with objects.
• These capabilities distinguish robots from other machines.

Answer: 1. Robot

Explanation:

• The tasks described, such as soldering, assembling, painting, and exploring, are performed by robots.
• Robots are versatile machines capable of performing a wide range of tasks.

Answer: 3. Robotics

Explanation:

• Robotics is the field of study that focuses on the design, construction, and operation of robots.
• It involves the interaction of robots with the physical world.

Answer: 1. Reactive control

Explanation:

• Reactive control is a robot control approach where the robot reacts to changes in its environment in real-time.
• This approach is commonly used in AI-driven robotics.

Answer: 2. Machine Learning (ML)

Explanation:

• Machine Learning (ML) enables systems to learn from data and improve their performance without being explicitly programmed.
• It is a core component of AI.

Answer: 4. All of the above

Explanation:

• Machine Learning (ML) involves algorithms that improve their performance over time with experience.
• These algorithms are designed to execute specific tasks and enhance their accuracy through learning.

Answer: 1. Machine Learning

Explanation:

• Machine Learning (ML) helps in understanding and improving the efficiency of human learning by analyzing patterns in data.
• It provides insights into how humans learn and adapt.

Answer: 4. All of above

Explanation:

• Rote learning, Induction learning, and Explanation-based learning are all forms of machine learning.
• These methods represent different approaches to learning from data.

Answer: 1. Rote learning

Explanation:

• Rote learning is based on memorization, where information is repeated until it is learned.
• It does not involve understanding or reasoning.

Answer: 2. Induction learning

Explanation:

• Induction learning involves deriving general rules or patterns from specific observed instances.
• It is a key method in machine learning for generalization.

Answer: 3. Explanation based learning

Explanation:

• Explanation-based learning focuses on learning from a single example by deriving a general rule or explanation.
• It is efficient for learning from limited data.

Answer: 1. Instance-based, Explanation based

Explanation:

• Instance-based learning relies heavily on data and examples.
• Explanation-based learning relies on prior knowledge and reasoning.

Answer: 3. Supervised

Explanation:

• Supervised learning algorithms are trained using labeled data, where the input-output pairs are provided.
• The model learns to map inputs to outputs based on the labeled examples.

Answer: 1. Un-supervised

Explanation:

• Unsupervised learning algorithms are trained using unlabeled data.
• The model identifies patterns or structures in the data without explicit guidance.

Answer: 3. Supervised

Explanation:

• Supervised learning models receive direct feedback in the form of labeled data to check the correctness of their predictions.
• This feedback helps the model improve its accuracy.

Answer: 1. Un-supervised

Explanation:

• Unsupervised learning models do not receive any feedback or labeled data.
• They rely on identifying patterns or clusters in the data without guidance.

Answer: 2. 80:20

Explanation:

• In supervised learning, the data is typically split into an 80:20 ratio, where 80% is used for training and 20% for testing.
• This split ensures that the model is trained on a sufficient amount of data while leaving enough for evaluation.

Answer: 1. Classification and Regression

Explanation:

• Classification and Regression are the two main types of supervised learning.
• Classification predicts discrete labels, while regression predicts continuous values.

Answer: 1. Classification

Explanation:

• Classification is the process of dividing a dataset into classes based on specific parameters.
• It is used to predict discrete labels for data points.

Answer: 2. Regression

Explanation:

• Regression is used to find the relationship between dependent and independent variables.
• It predicts continuous values based on input features.

Answer: 2. Classification

Explanation:

• The output variable “Purchased” is binary (0 or 1), indicating a classification problem.
• The goal is to classify whether a customer will purchase the product or not.

Answer: 1. Regression

Explanation:

• The output variable “Wind Speed” is continuous, indicating a regression problem.
• The goal is to predict the wind speed based on the input features.

Answer: 3. Association

Explanation:

• Association is a rule-based machine learning technique used to discover relationships between variables in large datasets.
• It is commonly used in market basket analysis.

Answer: 4. Clustering

Explanation:

• Clustering is used to group similar items together based on their characteristics.
• It is an unsupervised learning technique that identifies patterns in data.

Answer: 3. Reinforcement learning

Explanation:

• Reinforcement learning involves an agent that learns by receiving rewards or penalties for its actions.
• The model improves its performance based on the feedback it receives.

Answer: 3. Reinforcement learning

Explanation:

• Reinforcement learning uses a reward-punishment mechanism to train models.
• The agent learns to maximize rewards and minimize penalties.

Answer: 3. Reinforcement learning

Explanation:

• A robotic dog learning the movement of its arms through trial and error, receiving rewards for correct movements, is an example of reinforcement learning.
• The robot improves its performance based on feedback.

Answer: 3. Tree structure

Explanation:

• A decision tree builds models in the form of a tree structure, with nodes representing decisions and branches representing outcomes.
• It is used for both classification and regression tasks.

Answer: 4. Both A and B

Explanation:

• Decision trees can handle both categorical and continuous variables.
• They are versatile models that can be used for various types of data.

Answer: 3. Decision tree

Explanation:

• A decision tree is a graphical representation of decisions and their possible consequences.
• It is used for decision-making and predictive modeling.

Answer: 4. All of above

Explanation:

• Decision trees consist of decision nodes, chance nodes, and end nodes.
• These nodes represent different stages in the decision-making process.

Answer: 2. Squares

Explanation:

• In decision trees, squares are used to represent decision nodes.
• These nodes indicate points where a decision must be made.

Answer: 1. Circles

Explanation:

• In decision trees, circles are used to represent chance nodes.
• These nodes indicate points where outcomes are uncertain.

Answer: 3. Triangle

Explanation:

• In decision trees, triangles are used to represent end nodes.
• These nodes indicate the final outcome or result of a decision path.

Answer: 2. Bayesian learning

Explanation:

• Bayesian learning involves calculating the probability of each hypothesis given the data and making predictions based on these probabilities.
• It is a probabilistic approach to machine learning.