Get Smarter > Ω Street Smarts Ω > AI Basics Warm-Up > Flashcards

AI Basics Warm-Up Flashcards

Learn the core concepts and types of AI as a quick warm-up to AI Fundamentals. (80 cards)

Study These Flashcards
1
Q

Define:

Artificial Intelligence

(AI)

A

The field of study that focuses on creating systems capable of performing tasks that normally require human intelligence, such as reasoning, learning, and decision-making.

Examples include AI systems that can play chess, recommend movies, or help diagnose diseases.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is the primary goal of Artificial Intelligence?

A

To develop systems that can perform tasks that typically require human intelligence, such as understanding language, recognizing patterns, and solving problems.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Fill in the blank:

The early history of AI began in the ______ century.

A

20th

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Who is considered one of the founding figures of AI and created the Turing Test?

A

Alan Turing

The Turing Test is a measure of a machine’s ability to exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What was the significance of the Dartmouth Conference in 1956?

A

It is widely considered the birth of AI as a field of study, where the term ‘Artificial Intelligence’ was first coined.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

How does AI differ from traditional programming?

A

In traditional programming, rules are explicitly defined, whereas AI systems learn from data to create their own rules.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Define:

algorithm

A

A step-by-step procedure or set of rules designed to perform a task or solve a problem.

In AI, algorithms are used to process data and make decisions.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is a model in AI?

A

It is a logical representation of a system that is created by training an algorithm on data to perform tasks like predictions or classifications.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is inference in the context of AI?

A

It is the process of using a trained model to make predictions or decisions based on new data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Define:

dataset

A

A collection of data that is used to train and evaluate AI models.

Datasets can include text, images, numbers, and more.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What does it mean to train a model?

A

Adjusting its parameters using data so that it can perform specific tasks accurately.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is bias in AI?

A

It refers to systematic errors in a model’s predictions due to incorrect assumptions, often leading to unfair outcomes.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Fill in the blank:

When a model performs well on training data but poorly on new data, it is called ______.

A

overfitting

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Which term describes a situation where a model is too simple and can’t capture the complexity of the data?

A

underfitting

Underfitting often results in poor performance on both training and test data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is supervised learning?

A

A type of machine learning where the model is trained on labeled data, meaning the input comes with the correct output already known.

An example is training a model to recognize cats in photos, where each photo is labeled as ‘cat’ or ‘not cat’.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is unsupervised learning?

A

A type of machine learning where the model learns from unlabeled data, discovering patterns or structures without explicit instructions.

Clustering customers based on purchasing behavior is an example of unsupervised learning.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What is reinforcement learning?

A

A type of learning where an agent learns to make decisions by taking actions in an environment to maximize cumulative reward.

Think of teaching a dog tricks by rewarding it with treats for good behavior.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Fill in the blanks:

In reinforcement learning, an agent learns through ______ and ______.

A

trial; error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What is symbolic AI?

A

An approach to AI that uses explicit, human-readable symbols and rules to represent knowledge and reasoning processes.

Early AI systems like expert systems heavily relied on symbolic AI.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

How does symbolic AI differ from machine learning?

A
  • Symbolic AI uses predefined rules and logic.
  • Machine learning relies on data-driven learning to make predictions or decisions.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Fill in the blanks:

A hybrid AI system combines ______ and ______ techniques.

A

symbolic AI; machine learning

Hybrid systems can improve performance by integrating data-driven learning with rule-based reasoning.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Define:

feature engineering

A

The process of selecting, modifying, or creating input variables (features) that help improve the performance of a machine learning model.

Good feature engineering can significantly enhance the accuracy of a model.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Fill in the blank:

The dataset is split into ______ and testing sets to evaluate a model’s performance.

A

training

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

What is the purpose of the testing dataset?

A

To evaluate the performance of a trained machine learning model on new, unseen data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
What is **cross-validation** in the context of model evaluation?
A **technique for assessing** how a model will generalize to an independent dataset by training and testing the model multiple times with different data splits.
26
What is a **confusion matrix**?
A table used to **evaluate the performance of a classification model**, showing the true versus predicted classifications.
27
What is **accuracy** in the context of model evaluation?
The **proportion of correct predictions** made by a machine learning model out of all predictions made.
28
What is **precision** in model evaluation?
The ratio of true positive predictions to the total number of positive predictions made, measuring the **accuracy of positive predictions**.
29
What is **recall** in model evaluation?
The ratio of true positive predictions to the total number of actual positive cases, measuring the model's ability to **find all the relevant cases**.
30
# Define: neural network
It is a series of **algorithms** that attempts to recognize **underlying relationships** in a set of data through a process that **mimics the human brain**.
31
What is a **neuron** in the context of a neural network?
This is the **basic unit** in a **neural network** that receives input, processes it with weights, and **produces an output**.
32
What is an **activation function** in a neural network?
It is a **mathematical function** applied to a neuron's output to introduce **non-linearity** into the model.
33
Explain the concept of **backpropagation** in neural networks.
It is a **training algorithm** for **neural networks** that involves **adjusting weights** based on the **error rate** obtained in the previous epoch (iteration). ## Footnote This process involves calculating the gradient of the loss function with respect to each weight by the chain rule, allowing the model to learn.
34
What does **CNN** stand for, and what is it used for?
CNN stands for **Convolutional Neural Network**, and it is primarily used for **image processing tasks**, such as classification and object detection.
35
What is an **RNN**, and what **types of data** is it best suited for? | (Recurrent Neural Network)
This is a type of neural network designed to **recognize patterns in sequences of data** like time series or natural language.
36
What does **GAN** stand for, and what is its primary **function**?
GAN stands for **Generative Adversarial Network**, and it is used to generate new, synthetic instances of data that can **mimic** the original data.
37
# Fill in the blank: The main challenge with training deep neural networks is the \_\_\_\_\_\_ gradient problem.
vanishing
38
What is Natural Language Processing? | (NLP)
It is a field of **artificial intelligence** focused on enabling computers to **understand**, **interpret**, and **respond to human language**. ## Footnote Examples of NLP applications include virtual assistants, translation services, and sentiment analysis.
39
What is **pooling** in the context of CNNs, and why is it important?
This is a **down-sampling technique** used in CNNs to reduce the **spatial dimensions** of the feature maps, thereby lowering the computational cost and **controlling overfitting**.
40
Why are **transformers more efficient** than previous sequence models like RNNs?
Transformers can **process data in parallel**, unlike RNNs which process sequentially, **making transformers faster and more scalable**.
41
What is **tokenization** in NLP?
It is the process of **breaking down text into smaller units**, such as words or sentences, called tokens. ## Footnote Tokenization is the first step in text processing for many NLP tasks.
42
What are **word embeddings**?
These are **representations of words** as vectors in a continuous vector space, **capturing semantic meanings** and **relationships**. ## Footnote Popular word embedding models include Word2Vec and GloVe.
43
What is **sentiment analysis** in NLP?
It is the process of determining whether a **piece of text** expresses a **positive**, **negative**, or **neutral sentiment**. ## Footnote Commonly used in social media monitoring and customer feedback analysis.
44
What is a **Large Language Model**? | (LLM)
It is a type of artificial intelligence designed to **understand and generate human-like text** based on large amounts of text data. ## Footnote LLMs are used in applications like chatbots, translation services, and content creation.
45
What does the **architecture of LLMs** primarily rely on?
transformers ## Footnote Transformers are a type of neural network architecture that improves the handling of sequential data and parallel processing.
46
What is a **transformer** in the context of AI?
It is a neural network architecture that **uses self-attention mechanisms** to process and generate sequences of data efficiently.
47
What is the main **difference** between BERT and GPT?
* **BERT** is designed for understanding the context of words in a sentence (bidirectional). * **GPT** is designed for generating text (unidirectional). ## Footnote BERT processes text in both directions for better understanding, whereas GPT generates text in a forward manner.
48
What does **fine-tuning** mean in the context of LLMs?
It is the process of **adapting a pre-trained language model** to a specific task by training it further on a smaller, task-specific dataset.
49
# Fill in the blank: A common issue with LLMs is \_\_\_\_\_\_, where the model generates incorrect or nonsensical information.
hallucination
50
What is **ChatGPT**?
A conversational AI model developed by **OpenAI** that can generate **human-like text responses** based on prompts given to it. ## Footnote It is commonly used for applications like customer service bots and virtual assistants.
51
What is **Midjourney** known for?
An AI tool known for **generating images based on textual descriptions**, allowing users to create visual content through text prompts.
52
What is **Notion AI**?
An AI-powered tool integrated into the **Notion app** that assists with tasks such as summarizing content, generating ideas, and **automating repetitive tasks** within the Notion workspace.
53
What role does **specificity** play in prompt engineering?
It helps guide the AI model to generate more **relevant**, **targeted**, and **contextually appropriate** responses by reducing ambiguity in the prompt.
54
What is **prompt engineering** in the context of AI?
It is the process of **designing instructions** or input prompts to guide AI models, like language models, to produce **desired outputs**.
55
What is **role prompting**?
This involves **specifying a role** for the AI model to assume, such as acting as a teacher or a doctor, to influence its responses.
56
# Define: zero-shot prompting
It is when an AI model is asked to **perform a task without any specific examples** provided in the prompt.
57
# True or False: Few-shot prompting provides the AI with multiple examples before asking it to perform a task.
True ## Footnote Few-shot prompting involves showing the AI a few examples within the prompt to help it understand the desired task or format.
58
What is **prompt chaining**?
It involves using a series of prompts in sequence, where each prompt **builds on the previous response**, to achieve a more complex task.
59
What is a common application of **AI in healthcare**?
* diagnosing diseases * predicting patient outcomes * personalizing treatment plans ## Footnote For example, AI algorithms can analyze medical images to detect early signs of diseases like cancer.
60
How is AI **transforming education**?
* providing personalized learning experiences * automating administrative tasks * supporting tutors in identifying students' learning gaps ## Footnote Adaptive learning platforms use AI to adjust content based on student performance.
61
How can AI benefit **marketing strategies**?
* enabling personalized advertising * predicting consumer behavior * optimizing campaigns based on data insights ## Footnote Predictive analytics can help marketers identify potential customers and tailor messages.
62
In **robotics**, what is a typical use of AI?
* navigation * object recognition * performing complex tasks autonomously ## Footnote For instance, AI enables robots to navigate warehouses, avoiding obstacles and picking items.
63
What is **job automation**?
The use of technology, such as AI, to **perform tasks that were previously done by humans**. ## Footnote Examples include automated assembly lines in manufacturing and AI-driven chatbots in customer service.
64
Which **industry** is likely to see significant AI-driven job augmentation?
Finance ## Footnote In finance, AI assists in fraud detection, risk management, and automated trading while still involving human oversight and decision-making.
65
# Fill in the blank: Reskilling refers to training workers to learn new _______ to remain relevant in the job market.
skills
66
# Define: Big Data
It refers to **extremely large data sets** that are challenging to process and analyze using **traditional data-processing tools** due to their **volume**, **velocity**, and **variety**. ## Footnote Examples include social media data, sensor data, and transaction records from e-commerce platforms.
67
What is **cloud computing**?
The delivery of **computing services**, including **servers**, **storage**, **databases**, **networking**, and **software**, over the internet ('the cloud'). ## Footnote This allows for on-demand access to computing resources without the need for owning physical hardware.
68
What are **GPUs** and **TPUs** used for in AI?
GPUs (Graphics Processing Units) and TPUs (Tensor Processing Units) are **specialized hardware** designed to **accelerate the training and inference of machine learning models** by handling complex computations efficiently. ## Footnote GPUs are often used in gaming and graphics, while TPUs are specifically built by Google for machine learning tasks.
69
What does **GDPR** stand for?
General Data Protection Regulation ## Footnote GDPR is a regulation in the European Union that focuses on data protection and privacy for individuals.
70
Which **U.S. policy document** provides guidance on the ethical development of AI systems?
U.S. Executive Order on Maintaining American Leadership in Artificial Intelligence ## Footnote This order emphasizes promoting AI innovation while ensuring public trust and safety.
71
Name one **organization** dedicated to AI safety.
The Partnership on AI ## Footnote This organization collaborates to ensure that AI technologies are developed in a safe and ethical manner.
72
What is **cross-checking** in the context of AI outputs?
It involves **verifying AI outputs by comparing them with external sources** or **expert** opinions to ensure accuracy and reliability. ## Footnote This is important to prevent errors and ensure that AI systems provide trustworthy results.
73
Define the **ethical** use of AI.
Applying AI technologies in ways that **respect privacy**, **fairness**, **transparency**, and **accountability**, ensuring **no harm** comes to individuals or society. ## Footnote It involves considerations such as avoiding discrimination and protecting user data privacy.
74
# True or False: AI systems are sentient beings.
False ## Footnote AI systems do not have consciousness, emotions, or self-awareness; they operate based on algorithms and data.
75
What is a **myth** regarding **AI and job displacement**?
AI will completely **replace** all human jobs. ## Footnote While AI may automate some tasks, it also creates new job opportunities and can augment human roles, requiring collaboration between humans and machines.
76
What is a **Data Scientist**?
A **professional** who **analyzes and interprets complex data** to help organizations make informed decisions. ## Footnote Data scientists use statistical tools and programming languages to extract insights from data.
77
# True or False: A Machine Learning Engineer focuses primarily on building and deploying machine learning models.
True ## Footnote Machine Learning Engineers specialize in designing, training, and operationalizing models for real-world applications.
78
How did **Netflix** use AI to improve its user recommendations?
By using **collaborative filtering** and **deep learning** to personalize content based on user behavior. ## Footnote Netflix’s model increased viewer engagement by surfacing highly relevant content.
79
Microsoft Tay started tweeting **offensive content** shortly after launch. What caused this issue?
It learned **toxic behavior** from user interactions without content filtering. ## Footnote Tay revealed the danger of unsupervised learning in open environments.
80
What’s the fastest way to get up to speed on AI?
Brainscape’s [AI Fundamentals](https://www.brainscape.com/learn/ai-fundamentals?utm_source=crosslink&utm_medium=in-app&utm_campaign=in-app) Flashcards! ## Footnote Ideal for anyone who wants to grasp the **core principles of AI, machine learning, and deep learning** — and see how they shape the future of technology!
Ω Street Smarts Ω
flashcards
Decks in class (23)
# Cards
Brainscape helps you reach your goals faster, through stronger study habits.
© 2026 Bold Learning Solutions. Terms and Conditions