Connect two concepts Pick two concepts to see the shortest chain of sourced links between them.
FromRational agents Agent architectures (reflex, goal, utility, learning) Uninformed & heuristic search Local search & optimization Adversarial search & games Constraint satisfaction Logical agents & propositional logic First-order logic & inference Knowledge representation & ontologies Logic programming Classical planning Hierarchical planning Planning in nondeterministic domains Time, schedules & resources Bayesian networks Reasoning over time Probabilistic programming Decisions: MDPs, bandits, POMDPs Supervised learning (regression, classification, trees) Nonparametric models (kernels, nearest neighbors) Ensemble learning Unsupervised learning (clustering, dimensionality reduction) Statistical & probabilistic learning (EM) Feedforward networks Training & backpropagation Convolutional networks Recurrent networks Attention mechanism Generalization Unsupervised & transfer learning Passive & active reinforcement learning Policy search Apprenticeship & inverse RL Evolutionary algorithms Artificial life Language models Grammar & parsing Word embeddings Sequence-to-sequence models Transformer architecture Pretraining & transfer learning NLP tasks (translation, extraction, dialogue) Image formation & features Image classification Object detection The 3D world YOLO (real-time object detection) DETR (detection with transformers) Vision Transformer (ViT) Speech recognition Audio & speech processing Robotic perception Planning & control Reinforcement learning in robotics Humans & robots Non-cooperative game theory Cooperative game theory Collective decisions Cognitive science Can machines really think? Large language models Diffusion & image/video generation Multimodal models Fine-tuning & alignment Generative adversarial networks (GANs) Scaling laws Chain-of-thought reasoning Model Context Protocol (MCP) LLM-based agents & tool use Agent patterns: planning, memory, multi-agent Retrieval-augmented generation The limits of AI The ethics of AI The future of AI Swap ToRational agents Agent architectures (reflex, goal, utility, learning) Uninformed & heuristic search Local search & optimization Adversarial search & games Constraint satisfaction Logical agents & propositional logic First-order logic & inference Knowledge representation & ontologies Logic programming Classical planning Hierarchical planning Planning in nondeterministic domains Time, schedules & resources Bayesian networks Reasoning over time Probabilistic programming Decisions: MDPs, bandits, POMDPs Supervised learning (regression, classification, trees) Nonparametric models (kernels, nearest neighbors) Ensemble learning Unsupervised learning (clustering, dimensionality reduction) Statistical & probabilistic learning (EM) Feedforward networks Training & backpropagation Convolutional networks Recurrent networks Attention mechanism Generalization Unsupervised & transfer learning Passive & active reinforcement learning Policy search Apprenticeship & inverse RL Evolutionary algorithms Artificial life Language models Grammar & parsing Word embeddings Sequence-to-sequence models Transformer architecture Pretraining & transfer learning NLP tasks (translation, extraction, dialogue) Image formation & features Image classification Object detection The 3D world YOLO (real-time object detection) DETR (detection with transformers) Vision Transformer (ViT) Speech recognition Audio & speech processing Robotic perception Planning & control Reinforcement learning in robotics Humans & robots Non-cooperative game theory Cooperative game theory Collective decisions Cognitive science Can machines really think? Large language models Diffusion & image/video generation Multimodal models Fine-tuning & alignment Generative adversarial networks (GANs) Scaling laws Chain-of-thought reasoning Model Context Protocol (MCP) LLM-based agents & tool use Agent patterns: planning, memory, multi-agent Retrieval-augmented generation The limits of AI The ethics of AI The future of AI