Module 3: AI and Machine Learning

Question 1

Artificial Intelligence

Answer 1

The broad field of developing intelligent systems capable of performing tasks that typically require human intelligence

Question 2

Machine Learning

Answer 2

A subset of AI that allows machines to learn from data and improve performance on specific tasks

Question 3

Deep Learning

Answer 3

A subset of ML using neural networks with multiple layers to process complex patterns in data

Question 4

Neural Networks

Answer 4

AI systems inspired by the human brain; consisting of interconnected nodes (neurons) organized in layers

Question 5

Supervised Learning

Answer 5

ML approach where the algorithm learns from labeled data to make predictions on new; unlabeled data

Question 6

Unsupervised Learning

Answer 6

ML approach where the algorithm finds patterns and structures in unlabeled data without predefined categories

Question 7

Reinforcement Learning

Answer 7

ML approach where an agent learns to make decisions by interacting with an environment and receiving rewards or penalties

Question 8

Generative AI

Answer 8

AI systems capable of creating new; original content such as text; images; or audio

Question 9

Large Language Model (LLM)

Answer 9

Advanced AI models trained on vast amounts of text data to understand and generate human-like text

Question 10

Feature Engineering

Answer 10

The process of creating; transforming; and selecting relevant variables from raw data to improve ML model performance

Question 11

Overfitting

Answer 11

When a model performs well on training data but poorly on new; unseen data; indicating it has learned noise in the training set

Question 12

Underfitting

Answer 12

When a model fails to capture important patterns in the data; resulting in poor performance on both training and new data

Question 13

Hyperparameter Tuning

Answer 13

The process of optimizing model settings such as learning rate; batch size; and number of epochs to improve performance

Question 14

Bias (in AI)

Answer 14

Systematic errors in ML models that can lead to unfair or inaccurate predictions for certain groups

Question 15

Fairness

Answer 15

Ensuring that AI systems treat all individuals or groups equally and without discrimination

Question 16

Model Evaluation Metrics

Answer 16

Measures used to assess the performance of ML models; such as accuracy; precision; recall; F1 score; and AUC-ROC

Question 17

Responsible AI

Answer 17

The practice of developing and deploying AI systems in a way that is ethical; transparent; and beneficial to society

Question 18

MLOps

Answer 18

Practices for streamlining the machine learning lifecycle; including experimentation; automation; and continuous improvement

Question 19

Inferencing

Answer 19

The process of using a trained model to make predictions on new; unseen data

Question 20

Edge Computing

Answer 20

Running AI models on devices with limited computing power; often in environments with limited internet connectivity

Question 21

Prompt Engineering

Answer 21

The practice of crafting effective inputs for AI models to generate desired outputs; including techniques like zero-shot; few-shot; and chain-of-thought prompting

Question 22

Retrieval Augmented Generation (RAG)

Answer 22

A technique that combines retrieval of relevant information with generative AI to produce more accurate and contextually relevant responses

Question 23

Explainable AI

Answer 23

AI systems that provide human-understandable explanations for their decisions and outputs

Question 24

Fine-tuning

Answer 24

The process of adapting a pre-trained model to a specific task or domain by training it on a smaller; task-specific dataset

Question 25

Federated Learning

Answer 25

A machine learning technique that trains an algorithm across multiple decentralized devices or servers holding local data samples; without exchanging them