ZD_5_02 — Digital Preservation and the Longevity of Knowledge

Digital preservation — the set of policies, strategies, and actions required to ensure continued access to digital information over time — addresses one of the great paradoxes of the information age: humanity is producin

ZD_5_12 — Edge AI and TinyML: On-Device Machine Learning and Embedded Intelligence

Edge AI is the deployment of artificial intelligence algorithms on devices at the "edge" of the network — smartphones, embedded systems, cameras, sensors, wearables, industrial controllers, autonomous vehicles, and drone

ZD_4_02 — Game Theory, Strategic Interaction, and Cooperation

Game theory is the mathematical study of strategic interaction among rational agents, founded by John von Neumann and Oskar Morgenstern's Theory of Games and Economic Behavior (1944) and revolutionized by John Nash's equ

ZD_4_12 — Quantum Computing — Architecture, Algorithms, and Implications

Quantum computing — computation that exploits the principles of quantum mechanics (superposition, entanglement, and interference) to process information in ways fundamentally different from classical computers — represen

ZD_2_08 — Penrose and Computation: Non-Computability, Consciousness, and Gödel's Theorem

Roger Penrose (b. 1931), Nobel laureate in physics (2020, for demonstrating that black hole formation is a robust prediction of general relativity), has advanced an influential and controversial argument that human mathe

ZD_2_04 — Computer Vision and Image Processing

Computer vision — enabling machines to interpret and understand visual information from the world — has progressed from hand-crafted feature engineering to the deep learning revolution that now approaches or exceeds huma

ZD_2_16 — Federated Learning & Privacy-Preserving ML

Federated learning (FL) is a machine learning paradigm in which a model is trained across multiple decentralized devices or servers holding local data samples, without exchanging the raw data — the model comes to the dat

ZD_2_05 — Robotics and Control Theory

Robotics integrates mechanical engineering, electrical engineering, computer science, and control theory to design, build, and program machines that sense, reason, and act in the physical world. Control theory — the math

ZD_2_06 — Ethics of AI and Algorithmic Bias

AI ethics examines the moral implications of designing, deploying, and governing artificial intelligence systems, while algorithmic bias refers to systematic errors in automated decision-making that produce unfair outcom

ZD_2_15 — Transformer Architecture: Self-Attention and the Foundation of Modern AI

The transformer is a neural network architecture introduced in 2017 that replaced recurrent and convolutional models as the dominant paradigm in artificial intelligence. Its core innovation — the self-attention mechanism

ZD_2_02 — Artificial Intelligence Foundations

Artificial intelligence (AI) — the field devoted to creating machines that exhibit intelligent behavior — was formally founded at the Dartmouth Conference (1956) organized by John McCarthy, Marvin Minsky, Nathaniel Roche

ZD_2_07 — Artificial General Intelligence — Architectures and Challenges

Artificial General Intelligence (AGI) — a hypothetical AI system capable of performing any intellectual task that a human can, with the same flexibility, generality, and ability to learn and transfer knowledge across dom

ZD_2_12 — Generative AI: Large Language Models, Diffusion, and the Transformer Revolution

Generative AI refers to artificial intelligence systems capable of creating new content — text, images, audio, video, code, 3D models — that is novel, coherent, and often indistinguishable from human-created work. The fi

ZD_2_01 — Machine Learning Mathematics

Machine learning — the science of algorithms that improve through experience — rests on a rich mathematical foundation spanning optimization, statistics, linear algebra, probability, and functional analysis. The core mat

ZD_2_14 — Autonomous Systems: Self-Driving Vehicles, Drones, and Safety-Critical AI

Autonomous systems are machines capable of performing complex tasks in unstructured, dynamic environments with limited or no human intervention — perceiving their environment through sensors, making decisions through com

ZD_2_17 — AI Alignment & Existential Risk

AI alignment — the challenge of ensuring artificial intelligence systems pursue goals consistent with human values and intentions — has emerged as one of the defining technical and philosophical problems of the 21st cent

ZD_2_00 — AI Machine Learning: Subfolder Summary

ZD_2_13 — Explainable AI: Interpretability, Trust, and the Black Box Problem

Explainable AI (XAI) is the field concerned with making artificial intelligence systems — particularly complex machine learning models — understandable to humans. As AI systems increasingly make or influence high-stakes

ZD_2_09 — Recommender Systems: Collaborative Filtering, Content-Based, and Hybrid Approaches

Recommender systems (RecSys) are algorithms and architectures that predict user preferences and suggest relevant items — products, movies, music, news articles, social media posts, job listings, potential partners — from

ZD_2_11 — Reinforcement Learning: Agents, Rewards, and Sequential Decision-Making

Reinforcement learning (RL) is a paradigm of machine learning in which an agent learns to make sequential decisions by interacting with an environment, receiving rewards (or penalties) for its actions, and adjusting its