Module 2: AI Concepts, Terminology, and Application Domains

Looking for ‘introduction to artificial intelligence (AI) module 2 answers‘?

In this post, I provide accurate answers and detailed explanations for Module 2: AI Concepts, Terminology, and Application Domains of Course 1: Introduction to Artificial Intelligence (AI) – IBM Generative AI Engineering Professional Certificate

Whether you’re preparing for quizzes or brushing up on your knowledge, these insights will help you master the concepts effectively. Let’s dive into the correct answers and detailed explanations for each question.

Practice Quiz: Fundamental Concepts of AI

Practice Assignment

1. Imagine your company has recently installed cognitive computing systems for one of your banking customers. What is the primary advantage of using cognitive computing in the banking industry?

  • Improve customer support
  • Detect fraudulent transactions ✅
  • Automate the loan process
  • Manage network infrastructure

Explanation:
Cognitive computing mimics human reasoning and can analyze massive amounts of data to detect patterns and anomalies—making it highly effective at identifying fraudulent activities in banking. It supports real-time fraud detection by learning from past transaction behaviors and flagging irregularities.

  • Improving customer support and automating loans are benefits but not the primary advantage.
  • Managing network infrastructure is more related to IT operations, not cognitive AI.

2. Which type of AI has human-like cognitive abilities and can learn and adapt to a wide range of tasks beyond those required for a customer service chatbot?

  • Super AI
  • General AI ✅
  • Machine learning AI
  • Narrow AI

Explanation:
General AI (also called Strong AI) refers to machines with the ability to understand, learn, and apply intelligence to any task that a human can do. It is flexible and adaptive, unlike Narrow AI, which is task-specific.

  • Super AI is theoretical and more advanced than General AI (doesn’t exist yet).
  • Machine learning AI is a subset, not a type of AI in this classification.
  • Narrow AI only performs limited tasks like chatbots.

3. Choose a statement that best describes the process involved in convolutional neural networks (CNN).

  • It occurs through multiple layers, with each layer performing a convolution on the output from the previous layer. ✅
  • The neurons in hidden layers receive an input with a specific delay in time.
  • Each neuron in a layer receives input from neurons in the previous layer and then passes its output to neurons in the next layer.
  • A neural network combines two or more neural networks to arrive at the output.

Explanation:
CNNs (Convolutional Neural Networks) are especially used in image processing. They work by applying filters in convolutional layers, where each layer extracts features like edges, shapes, or patterns, building complexity over layers.

  • The other statements are either describing Recurrent Neural Networks (RNNs) or general neural nets, not specific to CNNs.

Practice Quiz: Domains of AI

Practice Assignment

4. Which of the following options can be considered as the primary role of computer vision in self-driving cars?

  • It reduces the need for physical sensors.
  • It generates maintenance schedules for the vehicle.
  • It enables the car to interpret visual cues and navigate safely. ✅
  • It completely eliminates the need for human drivers.

Explanation:
Computer vision allows self-driving cars to process and understand images from cameras and sensors. This includes detecting traffic signs, recognizing pedestrians, identifying lane boundaries, and avoiding obstacles—crucial for safe navigation.

  • It doesn’t eliminate human drivers completely—self-driving tech still requires oversight.
  • It supplements physical sensors, not replaces them.
  • Maintenance schedules are unrelated to vision.

5. What role does AI play in cloud computing?

  • AI helps analyze data, automate tasks, and make decisions, enhancing the use of data in cloud computing. ✅
  • AI replaces cloud computing by providing all the necessary data storage and analysis capabilities.
  • AI is only used to store data in cloud computing, with no impact on data analysis or decision-making.
  • AI only provides basic automation without evolving over time in cloud computing.

Explanation:
AI and cloud computing are complementary. Cloud provides the infrastructure and storage, while AI adds intelligence to automate tasks, analyze large-scale data, and make decisions. Together, they improve services like predictive analytics, customer insights, and automation.

6. Which of the following uses cloud computing to store and access data online from multiple devices?

  • Virtual reality (VR) headsets
  • Printers and scanners
  • Email services ✅
  • Desktop applications

Explanation:
Email services like Gmail or Outlook use cloud infrastructure so users can access their emails from any device via the internet. The data (emails, attachments) are stored in the cloud, not locally.

  • VR headsets can use cloud services but are not primarily cloud-based.
  • Printers/scanners and desktop apps are mostly local hardware/software and not inherently cloud-based.

Graded Quiz: AI Concepts, Terminology, and Application Domains

Graded Assignment

7. Choose the statement that correctly defines deep learning.

  • A type of data preprocessing
  • A technique for unsupervised learning
  • A set of simple algorithms for data analysis
  • A specialized subset of machine learning ✅

Explanation:
Deep learning is a subset of machine learning that uses artificial neural networks with many layers to model complex patterns in data.

8. What type of artificial neural network is commonly employed for tasks such as time-series analysis and natural language processing?

  • Perceptron neural networks
  • Deep feed-forward neural network
  • Feed-forward neural network
  • Recurrent neural network ✅

Explanation:
 RNNs are ideal for sequential data like text and time-series because they retain information from previous steps (i.e., they have “memory”).

9. Which of the following is the characteristic of a discriminator network?

  • Performs data augmentation
  • Creates data that looks real
  • Generates new data samples
  • Verifies generated data ✅

Explanation:
In a GAN (Generative Adversarial Network), the discriminator distinguishes between real and generated (fake) data.

10. Choose a statement that best describes how an IoT device works.

  • IoT devices collect data and send it via the internet to the cloud for storage and analysis. ✅
  • IoT devices continuously monitor their own battery levels and recharge automatically.
  • IoT devices analyze the local data and share it via Bluetooth.
  • IoT devices collect and store data locally. Then, they send it via the Internet to the cloud for analysis.

Explanation:
Most IoT devices gather data via sensors and transmit it over the internet to be analyzed and acted upon.

11. Which type of machine learning relies on providing an algorithm with a set of rules and constraints and letting it learn how to achieve its goals?

  • Transfer learning
  • Supervised learning
  • Reinforcement learning ✅
  • Unsupervised learning

Explanation:
Reinforcement learning teaches an agent to take actions in an environment by trial and error, guided by rewards and penalties.

12. Which of the following categories of machine learning uses a reward function to penalize bad actions or reward good actions?

  • Supervised learning
  • Neutral networks
  • Reinforcement learning ✅
  • Regression model

Explanation:
This form of learning involves agents that learn optimal behavior through reward-based feedback loops.

13. Which of the following statements best describes edge AI?

  • AI that allows devices to process data and make decisions locally ✅
  • AI that requires continuous internet connection to function
  • AI that relies exclusively on cloud-based processing
  • AI that only analyzes data in centralized data centers

Explanation:
Edge AI brings AI processing closer to the data source (e.g., smartphones, IoT), reducing latency and dependency on the cloud.

14. What is edge computing?

  • Edge computing is a technique that improves the display quality of video streaming services.
  • Edge computing is a technology that focuses on increasing the physical size of data storage devices.
  • Edge computing refers to processing data closer to where it is generated, such as on IoT devices, to reduce latency and bandwidth use. ✅
  • Edge computing means storing all data in a central cloud server for analysis.

Explanation:
Edge computing avoids sending all data to the cloud by processing data locally, improving speed and reducing bandwidth needs.

15. What is one of the primary reasons deep learning has gained popularity in recent years?

  • Deep learning only needs a small amount of labeled data to achieve high accuracy.
  • Deep learning is based on symbolic AI, which makes it easier to interpret and understand.
  • Deep learning requires minimal computational power, making it accessible to everyone.
  • Deep learning models can automatically extract features from raw data without the need for manual feature engineering. ✅

Explanation:
Traditional ML often required manual feature selection, but deep learning learns features automatically, especially useful in vision, NLP, etc.

16. What is the purpose of an activation function in a neural network?

  • To introduce non-linearity into the output of a neuron, enabling the network to learn complex patterns. ✅
  • To determine the learning rate of the network.
  • To initialize the weights of the network.
  • To control the flow of data within the input layer only.

Explanation:
Without activation functions, neural networks would behave like linear regression models and couldn’t model complex data patterns.

17. Which of these statements is true?

  • Cognitive systems can only process neatly organized structured data
  • Cognitive systems can only translate small volumes of audio data into their literal text translations at massive speeds
  • Cognitive systems can derive mathematically precise answers following a rigid decision tree approach
  • Cognitive systems can learn from their successes and failures ✅

Explanation:
Cognitive systems mimic human thought processes. They learn and adapt over time by analyzing data, recognizing patterns, and improving from interactions. Unlike rigid systems, cognitive systems don’t just follow pre-programmed instructions—they evolve based on feedback, making them more versatile and intelligent.

18. Which of these statements is true?

  • Al is the subset of Data Science that uses Deep Learning algorithms on structured big data
  • Deep Learning is a specialized subset of Machine Learning that uses layered neural networks to simulate human decision-making ✅
  • Data Science is a subset of Al that uses machine learning algorithms to extract meaning and draw inferences from data
  • Artificial Intelligence and Machine Learning refer to the same thing since both the terms are often used interchangeably

Explanation:
Deep Learning is a branch of AI where algorithms are structured in layers, mimicking the human brain’s neural networks. It excels at identifying patterns and improving decision-making over time. While AI encompasses a broad range of techniques, Deep Learning focuses specifically on these layered architectures.

19. Which of the following is NOT an attribute of Machine Learning?

  • Takes data and answers as input and uses these inputs to create a set of rules that determine what the Machine Learning model will be
  • Machine Learning defines behavioral rules by comparing large data sets to find common patterns
  • Takes data and rules as input and uses these inputs to develop an algorithm that will give us an answer ✅
  • Machine Learning models can be continuously trained

Explanation:
Machine Learning models require training data with inputs and their corresponding outputs to learn the relationships between them. This training allows the algorithm to create a model (rules) that can make predictions for new, unseen data. Machine Learning does not rely on predefined rules but discovers patterns and creates rules automatically.

20. Which of the following is NOT an attribute of Unsupervised Learning?

  • Takes data and rules as input and uses these inputs to develop an algorithm that will give us an answer ✅
  • The algorithm ingests unlabeled data, draws inferences, and finds patterns from unstructured data
  • It is useful for finding hidden patterns and or groupings in data and can be used to differentiate normal behavior with outliers such as fraudulent activity
  • It is useful for clustering data, where data is grouped according to how similar it is to its neighbors and dissimilar to everything else

Explanation:
Unsupervised learning involves analyzing unlabeled data to find patterns or groupings without predefined rules. Algorithms autonomously identify relationships, such as clusters or anomalies, making this approach valuable for tasks like market segmentation or fraud detection.

21. Which of the following is an attribute of Supervised Learning?

  • Relies on providing the machine learning algorithm unlabeled data and letting the machine infer qualities
  • Relies on providing the machine learning algorithm human-labeled data – the more samples you provide, the more precise the algorithm becomes in classifying new data ✅
  • Relies on providing the machine learning algorithm with a set of rules and constraints and letting it learn how to achieve its goals
  • Tries its best to maximize its rewards by trying different combinations of allowed actions within the provided constraints

Explanation:
In Supervised Learning, labeled datasets (where inputs are paired with correct outputs) train the algorithm. The more diverse and comprehensive the dataset, the better the model becomes at recognizing patterns and predicting outcomes for new data.

22. Which of the following statements about datasets used in Machine Learning is NOT true?

  • Validation data subset is used to validate results and fine-tune the algorithm’s parameters
  • Training subset is the data used to train the algorithm
  • Training data is used to fine-tune algorithm’s parameters and evaluate how good the model is ✅
  • Testing data is data the model has never seen before and is used to evaluate how good the model is

Explanation:
Training data is used solely to train the model. Validation data is used to adjust and fine-tune the model’s parameters, while testing data evaluates the model’s performance on new, unseen examples.

23. When creating deep learning algorithms, developers configure the number of layers and the type of functions that connect the outputs of each layer to the inputs of the next.

  • True ✅
  • False 

Explanation:
Deep Learning involves stacking multiple layers of neurons. Developers decide the number of layers and the mathematical functions connecting them. These layers process input data step-by-step, extracting complex features and patterns.

24. Which of the following fields of application for Al can be used at the airport to flag weapons within luggage passing through the X-ray scanner?

  • Chatbots
  • Computer Vision ✅
  • Natural Language
  • Speech

Explanation:
Computer Vision focuses on enabling machines to interpret and analyze visual data from the real world. At airports, it’s used to analyze X-ray images and detect objects like weapons.

25. Which of these activities is NOT required in order for a neural network to synthesize human voice?

  • Ingest numerous samples of a person’s voice until it can tell whether a new voice sample belongs to the same person
  • Deconstruct sentences to decipher the context of use ✅
  • Generate audio data and run it through the network to see if it validates it as belonging to the subject
  • Continue to correct the sample and run it through the classifier, repetitively, till an accurate voice sample is created

Explanation:
Speech synthesis focuses on creating human-like speech by analyzing voice data, generating audio, and refining it. Deconstructing sentence context is a task of Natural Language Processing, not speech synthesis.

26. Which one of these ways is NOT how Al learns?

  • Supervised Learning
  • Unsupervised Learning
  • Proactive Learning ✅
  • Reinforcement Learning

Explanation:
AI learns using three primary methods:

  1. Supervised Learning: Training on labeled datasets.
  2. Unsupervised Learning: Discovering patterns in unlabeled data.
  3. Reinforcement Learning: Learning by trial and error to maximize rewards.
    “Proactive Learning” is not a recognized AI learning method.

Related contents:

Module 1: Introduction and Applications of AI
Module 3: Business and Career Transformation Through AI
Module 4: Issues, Concerns, and Ethical Considerations

You might also like:

Course 1: Introduction to Software Engineering
Course 3: Generative AI: Introduction and Applications
Course 4: Generative AI: Prompt Engineering Basics
Course 5: Introduction to HTML, CSS, & JavaScript
Course 6: Python for Data Science, AI & Development
Course 7: Developing AI Applications with Python and Flask
Course 8: Building Generative AI-Powered Applications with Python
Course 9: Generative AI: Elevate your Software Development Career
Course 10: Software Developer Career Guide and Interview Preparation

Leave a Reply