Key Concepts in Artificial Intelligence and Machine Learning
Study online at https://quizlet.com/_hjzpo3
1. Artificial Intelli- The development of machines or software that can perform tasks typically requir-
gence (AI) ing human intelligence, such as learning, reasoning, understanding language,
and making decisions.
2. High Level Natural Language Processing (NLP)
Overview 2 Natural Language Understanding (NLU)
Natural Language Generation (NLG)
Language Models
Bag-of-Words (BoW)
Word Embedding
Probabilistic Context-Free Grammar (PCFG)
Tokenization & Syntax
Applications
Chatbots & Virtual Assistants
Sentiment Analysis
Machine Translation
Text Summarization
Neural Network Architectures
Feed Forward Neural Network (FFNN)
Recurrent Neural Network (RNN)
Long Short-Term Memory (LSTM)
Bidirectional RNN
Convolutional Neural Network (CNN)
Transformers
Self-Attention
Multiheaded Attention
Sequence-to-Sequence Models
,Key Concepts in Artificial Intelligence and Machine Learning
Study online at https://quizlet.com/_hjzpo3
Decoding Strategies
Greedy Decoding
Beam Search
Reinforcement Learning
Passive vs. Active RL
Sparse Rewards
Q-Learning
Q-Function
Deep Q Networks (DQN)
Model-Free vs. Model-Based Learning
Policy Search
Bang-Bang Control (e.g., Cart-Pole)
Data & Ethics
Data Privacy
De-identification & Re-identification
K-Anonymity
Aggregate Querying
Differential Privacy
Federated Learning
Secure Aggregation
Data Quality
Accuracy, Completeness, Uniformity
Bias & Fairness
Data Transformation
Box-Cox Power Transformation
Normalization & Standardization
Flattening, Delta, Digest
Feature Engineering
Feature Creation & Selection
One-Hot Encoding
, Key Concepts in Artificial Intelligence and Machine Learning
Study online at https://quizlet.com/_hjzpo3
Interaction Features
Recursive Feature Elimination
3. AI Hierarchy Artificial Intelligence (AI) -AI Framework - The broadest field focused on building
systems that can simulate human intelligence, including reasoning, learning,
perception, and language understanding.
Machine Learning (ML) -AI Subfield - A subset of AI where systems improve
performance by learning patterns from data rather than being explicitly pro-
grammed.
Deep Learning (DL) -Machine Learning Subfield - A specialized form of machine
learning that uses layered neural networks to model complex patterns in large
datasets, especially effective for image, speech, and text analysis.
Natural Language Processing (NLP) -AI Subfield - The area of AI focused on
enabling machines to understand, interpret, and generate human language. It
intersects with both machine learning and deep learning techniques.
4. High Level AI Foundations
Overview 1 Rational Agents
Percepts & Percept Sequences
Agent Function vs. Agent Program
PEAS (Performance, Environment, Actuators, Sensors)
Environment Types
Fully Observable vs. Partially Observable
Deterministic vs. Stochastic
Episodic vs. Sequential
Static vs. Dynamic
, Key Concepts in Artificial Intelligence and Machine Learning
Study online at https://quizlet.com/_hjzpo3
Discrete vs. Continuous
Decision-Making
Belief States & Contingency Plans
Maximum Expected Utility (MEU)
Logical Qualification Problem
AI Ethics
Value Alignment
Transparency & Accountability
Differential Privacy
Lethal Autonomous Weapons
Knowledge Representation
Ontologies
Upper Ontology
General-Purpose Ontology
Special-Purpose Ontology
Ontological Engineering
Semantic Networks
Description Logics
Subsumption
Classification
Consistency Checking
Event Calculus
Fluents, Events, Objects
Modal Logic
Modal Operators (e.g., K_A(P))
Propositional Attitudes
Referential Transparency
Referential Opacity
Learning in AI
Paradigms
Study online at https://quizlet.com/_hjzpo3
1. Artificial Intelli- The development of machines or software that can perform tasks typically requir-
gence (AI) ing human intelligence, such as learning, reasoning, understanding language,
and making decisions.
2. High Level Natural Language Processing (NLP)
Overview 2 Natural Language Understanding (NLU)
Natural Language Generation (NLG)
Language Models
Bag-of-Words (BoW)
Word Embedding
Probabilistic Context-Free Grammar (PCFG)
Tokenization & Syntax
Applications
Chatbots & Virtual Assistants
Sentiment Analysis
Machine Translation
Text Summarization
Neural Network Architectures
Feed Forward Neural Network (FFNN)
Recurrent Neural Network (RNN)
Long Short-Term Memory (LSTM)
Bidirectional RNN
Convolutional Neural Network (CNN)
Transformers
Self-Attention
Multiheaded Attention
Sequence-to-Sequence Models
,Key Concepts in Artificial Intelligence and Machine Learning
Study online at https://quizlet.com/_hjzpo3
Decoding Strategies
Greedy Decoding
Beam Search
Reinforcement Learning
Passive vs. Active RL
Sparse Rewards
Q-Learning
Q-Function
Deep Q Networks (DQN)
Model-Free vs. Model-Based Learning
Policy Search
Bang-Bang Control (e.g., Cart-Pole)
Data & Ethics
Data Privacy
De-identification & Re-identification
K-Anonymity
Aggregate Querying
Differential Privacy
Federated Learning
Secure Aggregation
Data Quality
Accuracy, Completeness, Uniformity
Bias & Fairness
Data Transformation
Box-Cox Power Transformation
Normalization & Standardization
Flattening, Delta, Digest
Feature Engineering
Feature Creation & Selection
One-Hot Encoding
, Key Concepts in Artificial Intelligence and Machine Learning
Study online at https://quizlet.com/_hjzpo3
Interaction Features
Recursive Feature Elimination
3. AI Hierarchy Artificial Intelligence (AI) -AI Framework - The broadest field focused on building
systems that can simulate human intelligence, including reasoning, learning,
perception, and language understanding.
Machine Learning (ML) -AI Subfield - A subset of AI where systems improve
performance by learning patterns from data rather than being explicitly pro-
grammed.
Deep Learning (DL) -Machine Learning Subfield - A specialized form of machine
learning that uses layered neural networks to model complex patterns in large
datasets, especially effective for image, speech, and text analysis.
Natural Language Processing (NLP) -AI Subfield - The area of AI focused on
enabling machines to understand, interpret, and generate human language. It
intersects with both machine learning and deep learning techniques.
4. High Level AI Foundations
Overview 1 Rational Agents
Percepts & Percept Sequences
Agent Function vs. Agent Program
PEAS (Performance, Environment, Actuators, Sensors)
Environment Types
Fully Observable vs. Partially Observable
Deterministic vs. Stochastic
Episodic vs. Sequential
Static vs. Dynamic
, Key Concepts in Artificial Intelligence and Machine Learning
Study online at https://quizlet.com/_hjzpo3
Discrete vs. Continuous
Decision-Making
Belief States & Contingency Plans
Maximum Expected Utility (MEU)
Logical Qualification Problem
AI Ethics
Value Alignment
Transparency & Accountability
Differential Privacy
Lethal Autonomous Weapons
Knowledge Representation
Ontologies
Upper Ontology
General-Purpose Ontology
Special-Purpose Ontology
Ontological Engineering
Semantic Networks
Description Logics
Subsumption
Classification
Consistency Checking
Event Calculus
Fluents, Events, Objects
Modal Logic
Modal Operators (e.g., K_A(P))
Propositional Attitudes
Referential Transparency
Referential Opacity
Learning in AI
Paradigms
