📚 AI Survey Compendium (1950s–2025)

Welcome to the AI Survey Compendium, a curated collection of 18 surveys covering the historical evolution, breakthroughs, and modern advancements across different fields of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL).

Each survey is written in a structured timeline + insights format, making it useful for students, researchers, and practitioners who want a comprehensive yet concise reference.

📑 Table of Contents

Core Learning Paradigms

Supervised Learning in AI: ML → DL Evolution
Unsupervised Learning in AI, ML, and Deep Learning
Semi-Supervised Learning in Deep Learning
Self-Supervised Learning (SSL) Breakthroughs
Reinforcement Learning in Machine Learning
Reinforcement Learning + Deep Learning Breakthroughs

Core Tasks

Classification in AI: ML → DL Evolution
Regression in AI: ML → DL Evolution
Clustering in AI: ML → DL Evolution
Dimensionality Reduction in AI: ML → DL Evolution

Neural Architectures

Feedforward Neural Networks (FNN) Timeline & Breakthroughs
Convolutional Neural Networks (CNN) Breakthroughs (1980s–2025)
Recurrent Neural Networks (RNN) & NLP Breakthroughs (1950s–2025)
Transformer-Based Models in Deep Learning (2017–2025)
Graph Neural Networks (GNN) Breakthroughs

Generative & Probabilistic Models

Probabilistic Models in Deep Learning (1980s–2025)
Generative Algorithms in Deep Learning (AEs, GANs, Flows, Diffusion)
Evolution of Flow-Based and Diffusion Models (2015–2025)

📝 Format & Style

Each survey is structured as:

🔹 Definition / Abstract – quick overview.
📜 Historical Timeline – chronological breakthroughs.
⚙️ Methodology / Core Ideas – algorithms, architectures.
📊 Results & Applications – impact and use cases.
✅ Key Insights – summary and lessons learned.

Mathematical equations are written in LaTeX/Markdown math format, ensuring readability in Jupyter/Colab.

🎯 Purpose

Serve as a reference hub for the evolution of AI research fields.
Help learners connect classical ML with modern DL breakthroughs.
Provide survey-style notes for teaching, research, or personal study.

📌 How to Use

Browse surveys directly in Markdown (.md) format.
Use as learning notes, teaching material, or literature survey references.
Extend the repo by adding new surveys for 2025+ research trends.

🏆 Credits

Compiled and structured by [Your Name / Handle].
Inspired by milestone papers from academia and industry (Google, OpenAI, DeepMind, Meta AI, Microsoft Research).

📖 License

This project is released under the MIT License.
Free to use, share, and extend with proper attribution.

🚀 This repo is a one-stop survey archive — connecting the dots across decades of AI progress.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Repository files navigation

📚 AI Survey Compendium (1950s–2025)

📑 Table of Contents

Core Learning Paradigms

Core Tasks

Neural Architectures

Generative & Probabilistic Models

📝 Format & Style

🎯 Purpose

📌 How to Use

🏆 Credits

📖 License

About

Uh oh!

Releases

Packages

Languages

Name		Name	Last commit message	Last commit date
Latest commit History 27 Commits
A_Chronological_Cartography_of_Attention_Mechanisms_From_Gradient_Collapse_to_Transformers_and_Beyond.ipynb		A_Chronological_Cartography_of_Attention_Mechanisms_From_Gradient_Collapse_to_Transformers_and_Beyond.ipynb
CNN Breakthroughs in Deep Learning (1980s–2025).ipynb		CNN Breakthroughs in Deep Learning (1980s–2025).ipynb
Chronological_Evolution_of_Machine_Translation_(MT).ipynb		Chronological_Evolution_of_Machine_Translation_(MT).ipynb
Classification in AI_ ML → DL Evolution.ipynb		Classification in AI_ ML → DL Evolution.ipynb
Clustering Loss Functions in AI_ML_DL.ipynb		Clustering Loss Functions in AI_ML_DL.ipynb
Clustering in AI_ ML → DL Evolution.ipynb		Clustering in AI_ ML → DL Evolution.ipynb
Clustering_Evaluation_Metrics_(AI_ML_DL).ipynb		Clustering_Evaluation_Metrics_(AI_ML_DL).ipynb
Comprehensive_List_of_Feature_Representations_in_AI_and_Math.ipynb		Comprehensive_List_of_Feature_Representations_in_AI_and_Math.ipynb
Comprehensive_List_of_Techniques_Supporting_Deep_Model_Training.ipynb		Comprehensive_List_of_Techniques_Supporting_Deep_Model_Training.ipynb
Comprehensive_Ontology_of_Artificial_Intelligence_Learning_Paradigms_Theory,_Algorithms,_and_Applications.ipynb		Comprehensive_Ontology_of_Artificial_Intelligence_Learning_Paradigms_Theory,_Algorithms,_and_Applications.ipynb
Dimensionality Reduction in AI_ ML → DL Evolution.ipynb		Dimensionality Reduction in AI_ ML → DL Evolution.ipynb
Ecosystem_of_an_AI_Model_with_References.ipynb		Ecosystem_of_an_AI_Model_with_References.ipynb
Evaluation Metrics for Classification in AI_ML_DL.ipynb		Evaluation Metrics for Classification in AI_ML_DL.ipynb
Evaluation Metrics for Dimensionality Reduction (AI_ML_DL).ipynb		Evaluation Metrics for Dimensionality Reduction (AI_ML_DL).ipynb
Evaluation Metrics in Regression (AI_ML_DL).ipynb		Evaluation Metrics in Regression (AI_ML_DL).ipynb
Feedforward Neural Networks (FNN) Timeline & Breakthroughs.ipynb		Feedforward Neural Networks (FNN) Timeline & Breakthroughs.ipynb
Foundational_Taxonomy_of_Generative_AI_Mechanisms,_Application_Modalities,_and_Canonical_Papers.ipynb		Foundational_Taxonomy_of_Generative_AI_Mechanisms,_Application_Modalities,_and_Canonical_Papers.ipynb
From_Cognitive_Attention_to_Generative_Transformers_A_Chronological_Evolution_of_Subfields_(1970–2025).ipynb		From_Cognitive_Attention_to_Generative_Transformers_A_Chronological_Evolution_of_Subfields_(1970–2025).ipynb
From_IBM_Models_to_LLMs_A_Chronological_Survey_of_Breakthroughs_in_Machine_Translation_(1993–2023).ipynb		From_IBM_Models_to_LLMs_A_Chronological_Survey_of_Breakthroughs_in_Machine_Translation_(1993–2023).ipynb
From_Neocognitron_to_Vision_Transformers_A_Chronological_Evolution_of_Convolutional_Neural_Network_Subfields_(1900–2025).ipynb		From_Neocognitron_to_Vision_Transformers_A_Chronological_Evolution_of_Convolutional_Neural_Network_Subfields_(1900–2025).ipynb
From_Probabilistic_Roots_to_Multimodal_LLMs_A_Chronological_Evolution_of_Generative_AI_Subfields_(1900–2025).ipynb		From_Probabilistic_Roots_to_Multimodal_LLMs_A_Chronological_Evolution_of_Generative_AI_Subfields_(1900–2025).ipynb
Generative Algorithms in Deep Learning.ipynb		Generative Algorithms in Deep Learning.ipynb
Graph Neural Networks (GNNs) Breakthroughs.ipynb		Graph Neural Networks (GNNs) Breakthroughs.ipynb
Key_Papers_on_Google_related_Machine_Translation_(MT).ipynb		Key_Papers_on_Google_related_Machine_Translation_(MT).ipynb
Loss Functions for Classification in AI (ML & DL).ipynb		Loss Functions for Classification in AI (ML & DL).ipynb
Loss Functions in Dimensionality Reduction (AI_ML_DL).ipynb		Loss Functions in Dimensionality Reduction (AI_ML_DL).ipynb
Meta_Learning_Across_Time_A_Concise_Chronological_Framework_of_Concepts,_Methods,_and_Milestones_in_Learning_to_Learn.ipynb		Meta_Learning_Across_Time_A_Concise_Chronological_Framework_of_Concepts,_Methods,_and_Milestones_in_Learning_to_Learn.ipynb
Multimodal Deep Learning Breakthroughs.ipynb		Multimodal Deep Learning Breakthroughs.ipynb
Multimodal_Deep_Learning_—_A_Field_Guide_(2014–2025).ipynb		Multimodal_Deep_Learning_—_A_Field_Guide_(2014–2025).ipynb
NLP & RNN Breakthroughs in Deep Learning (1950s–2025).ipynb		NLP & RNN Breakthroughs in Deep Learning (1950s–2025).ipynb
Optimization Techniques in AI, ML, and Deep Learning.ipynb		Optimization Techniques in AI, ML, and Deep Learning.ipynb
Probabilistic Models in Deep Learning (1980s–2025).ipynb		Probabilistic Models in Deep Learning (1980s–2025).ipynb
README.md		README.md
Regression Losses in AI_ML_DL.ipynb		Regression Losses in AI_ML_DL.ipynb
Regression in AI_ ML → DL Evolution.ipynb		Regression in AI_ ML → DL Evolution.ipynb
Regularization Techniques in AI, ML, and DL.ipynb		Regularization Techniques in AI, ML, and DL.ipynb
Reinforcement Learning + Deep Learning Breakthroughs.ipynb		Reinforcement Learning + Deep Learning Breakthroughs.ipynb
Reinforcement Learning in Machine Learning.ipynb		Reinforcement Learning in Machine Learning.ipynb
Self-Supervised Learning (SSL) Breakthroughs.ipynb		Self-Supervised Learning (SSL) Breakthroughs.ipynb
Semi-Supervised Learning (Semi-SL) in Deep Learning.ipynb		Semi-Supervised Learning (Semi-SL) in Deep Learning.ipynb
Supervised Learning in AI_ ML → DL Evolution.ipynb		Supervised Learning in AI_ ML → DL Evolution.ipynb
The_Bitter_Lessons_Historical_Patterns_of_Computation,_Learning,_and_the_Decline_of_Human_Crafted_Knowledge_in_AI.ipynb		The_Bitter_Lessons_Historical_Patterns_of_Computation,_Learning,_and_the_Decline_of_Human_Crafted_Knowledge_in_AI.ipynb
The_Chronological_Evolution_of_NLP_Subfields_(1900–2025)_From_Symbolic_Rules_to_Large_Language_Models.ipynb		The_Chronological_Evolution_of_NLP_Subfields_(1900–2025)_From_Symbolic_Rules_to_Large_Language_Models.ipynb
The_Evolutionary_Trajectory_of_Convolutional_Neural_Networks_From_Biological_Inspiration_to_Hybrid_Architectures_(1959–2025).ipynb		The_Evolutionary_Trajectory_of_Convolutional_Neural_Networks_From_Biological_Inspiration_to_Hybrid_Architectures_(1959–2025).ipynb
The_Evolutionary_Trajectory_of_Deep_Learning_RNN_Foundations,_CNN_Advances,_and_the_Rise_of_Attention_Mechanisms.ipynb		The_Evolutionary_Trajectory_of_Deep_Learning_RNN_Foundations,_CNN_Advances,_and_the_Rise_of_Attention_Mechanisms.ipynb
The_Evolutionary_Trajectory_of_Recurrent_Neural_Networks_From_Biological_Roots_to_Computational_Decline_(1901–2025).ipynb		The_Evolutionary_Trajectory_of_Recurrent_Neural_Networks_From_Biological_Roots_to_Computational_Decline_(1901–2025).ipynb
The_Skeleton_of_Artificial_Intelligence_Linear,_Nonlinear,_and_Backpropagation_as_the_Genetic_Code_of_Learning_Systems.ipynb		The_Skeleton_of_Artificial_Intelligence_Linear,_Nonlinear,_and_Backpropagation_as_the_Genetic_Code_of_Learning_Systems.ipynb
Time Series Models & Deep Learning Timeline (1900s–2025).ipynb		Time Series Models & Deep Learning Timeline (1900s–2025).ipynb
Transformer Variants in Deep Learning.ipynb		Transformer Variants in Deep Learning.ipynb
Unsupervised Learning in AI, ML, and Deep Learning.ipynb		Unsupervised Learning in AI, ML, and Deep Learning.ipynb
Unsupervised _ Representation Learning Breakthroughs.ipynb		Unsupervised _ Representation Learning Breakthroughs.ipynb

Programming-Ocean-Academy/ai-timeline-surveys-concepts-algorithms

Folders and files

Latest commit

History

Repository files navigation

📚 AI Survey Compendium (1950s–2025)

📑 Table of Contents

Core Learning Paradigms

Core Tasks

Neural Architectures

Generative & Probabilistic Models

📝 Format & Style

🎯 Purpose

📌 How to Use

🏆 Credits

📖 License

About

Resources

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Languages

Packages