Module 3: AI and Machine Learning Flashcards
Artificial Intelligence
The broad field of developing intelligent systems capable of performing tasks that typically require human intelligence
Machine Learning
A subset of AI that allows machines to learn from data and improve performance on specific tasks
Deep Learning
A subset of ML using neural networks with multiple layers to process complex patterns in data
Neural Networks
AI systems inspired by the human brain; consisting of interconnected nodes (neurons) organized in layers
Supervised Learning
ML approach where the algorithm learns from labeled data to make predictions on new; unlabeled data
Unsupervised Learning
ML approach where the algorithm finds patterns and structures in unlabeled data without predefined categories
Reinforcement Learning
ML approach where an agent learns to make decisions by interacting with an environment and receiving rewards or penalties
Generative AI
AI systems capable of creating new; original content such as text; images; or audio
Large Language Model (LLM)
Advanced AI models trained on vast amounts of text data to understand and generate human-like text
Feature Engineering
The process of creating; transforming; and selecting relevant variables from raw data to improve ML model performance
Overfitting
When a model performs well on training data but poorly on new; unseen data; indicating it has learned noise in the training set
Underfitting
When a model fails to capture important patterns in the data; resulting in poor performance on both training and new data
Hyperparameter Tuning
The process of optimizing model settings such as learning rate; batch size; and number of epochs to improve performance
Bias (in AI)
Systematic errors in ML models that can lead to unfair or inaccurate predictions for certain groups
Fairness
Ensuring that AI systems treat all individuals or groups equally and without discrimination
Model Evaluation Metrics
Measures used to assess the performance of ML models; such as accuracy; precision; recall; F1 score; and AUC-ROC
Responsible AI
The practice of developing and deploying AI systems in a way that is ethical; transparent; and beneficial to society
MLOps
Practices for streamlining the machine learning lifecycle; including experimentation; automation; and continuous improvement
Inferencing
The process of using a trained model to make predictions on new; unseen data
Edge Computing
Running AI models on devices with limited computing power; often in environments with limited internet connectivity
Prompt Engineering
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
Retrieval Augmented Generation (RAG)
A technique that combines retrieval of relevant information with generative AI to produce more accurate and contextually relevant responses
Explainable AI
AI systems that provide human-understandable explanations for their decisions and outputs
Fine-tuning
The process of adapting a pre-trained model to a specific task or domain by training it on a smaller; task-specific dataset
Federated Learning
A machine learning technique that trains an algorithm across multiple decentralized devices or servers holding local data samples; without exchanging them
