Define:
algorithm
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.
What is a model in AI?
It is a logical representation of a system that is created by training an algorithm on data to perform tasks like predictions or classifications.
True or False:
In AI, a model is the same as an algorithm.
False
An algorithm is the process used to create a model, which is the output that can make predictions or decisions.
What is inference in the context of AI?
It is the process of using a trained model to make predictions or decisions based on new data.
Fill in the blank:
The process of training a model involves feeding it ______ to learn patterns.
data
Define:
dataset
A collection of data that is used to train and evaluate AI models.
Datasets can include text, images, numbers, and more.
What does it mean to train a model?
Adjusting its parameters using data so that it can perform specific tasks accurately.
True or False:
Datasets are only used during the training of AI models.
False
Datasets are used during both training and evaluation to test model performance.
What is bias in AI?
It refers to systematic errors in a model’s predictions due to incorrect assumptions, often leading to unfair outcomes.
Fill in the blank:
When a model performs well on training data but poorly on new data, it is called ______.
overfitting
Define:
overfitting
It occurs when a model learns the training data too well, including its noise and outliers, and performs poorly on unseen data.
What is the difference between training and inference?
- Training involves learning patterns from data to create a model.
- Inference involves using this model to make decisions on new data.
Which term describes a situation where a model is too simple and can’t capture the complexity of the data?
underfitting
Underfitting often results in poor performance on both training and test data.
True or False:
Bias in AI can lead to unfair or discriminatory outcomes.
True
AI systems can reflect and amplify biases present in training data, leading to unfair or discriminatory results.
What role do algorithms play in the development of AI models?
It defines the steps and logic used to process data and adjust the model’s parameters during training.
Fill in the blanks:
A ______ ______ is used to evaluate the accuracy of an AI model.
test dataset
Why is it important to have a diverse dataset when training an AI model?
It helps ensure the model learns a wide range of patterns, reducing bias and improving generalization.
What can be done to reduce overfitting?
Techniques like cross-validation, regularization, and using more training data can help reduce overfitting.
True or False:
A model that generalizes well performs accurately on both seen and unseen data.
True
Generalization refers to a model’s ability to maintain high performance on new, unseen data—not just the data it was trained on.
What is a training dataset?
It is a subset of data used to teach a model by adjusting its parameters.
Fill in the blank:
______ is the process of drawing conclusions from data using a model.
Inference
What is the purpose of a validation dataset?
This is used to tune the model’s parameters and prevent overfitting during training.
How is inference used with a model in a real-world application?
Inference is the process of using a trained model to make predictions or decisions on new data, such as recommending products to users.
Training is when a model learns patterns from data. Inference is when the trained model is applied to new inputs in production or real-world use.
Fill in the blanks:
______ ______ is a key factor in ensuring the fairness and accuracy of AI models.
Bias mitigation
-
Introduction to AI20
-
Key Terminology & Concepts29
-
Prompt Engineering Techniques29
-
Types of AI & Learning Approaches17
-
Machine Learning Foundations25
-
Neural Networks & Deep Learning25
-
Natural Language Processing (NLP)18
-
Large Language Models (LLMs)20
-
AI Tools in Practice51
-
Use Cases & Applications20
-
AI and the Future of Work10
-
Data & AI Infrastructure15
-
AI Regulation & Governance10
-
AI Best Practices28
-
Common Myths & Misconceptions10
-
Career Paths in AI10
-
Quick Case Studies25
