Wednesday, August 20, 2025

// // Leave a Comment

LAZAR - Appendix to The Prophets of the Thinking Machines: Surveys on Continual Learning, Reinforcement Learning, Computer Vision from 1960s to 2020s, Transformers, Speech Recognition, Evolutionary and Genetic Programming ...

 

THE SACRED COMPUTER  
TODOR ARNAUDOV - TOSH

LAZAR

THE PROPHETS OF THE
THINKING MACHINES
ARTIFICIAL GENERAL INTELLIGENCE & TRANSHUMANISM

 

 


HISTORY THEORY AND PIONEERS
PAST PRESENT AND FUTURE



by the author of the world’s first university course in
Artificial General Intelligence and the
Theory of Universe and Mind



ПРОРОЦИТЕ НА МИСЛЕЩИТЕ МАШИНИ
ИЗКУСТВЕН РАЗУМ И РАЗВИТИЕ НА ЧОВЕКА
ИСТОРИЯ ТЕОРИЯ И ПИОНЕРИ; МИНАЛО НАСТОЯЩЕ И БЪДЕЩЕ



* First edition: 20.8.2025 (To be continued and refined)
* 128 Pages

Edition: 20.8.2025

http://twenkid.com/agi

For now download from: https://github.com/twenkid/sigi-2025
(...)  
 


© Authors: All cited original authors
                        and Todor Arnaudov – author of The Prophets of the Thinking Machines and editor: selecton of authors, papers, concepts, citations; summaries notes etc.

The Sacred Computer: Thinking Machines, Creativity and Human Development


 

You can join or help The Sacred Computer!

...

(...)

#lotsofpapers  #lazar

 

Lots of Papers: ] In AI, ML, CV, ANN, DL, …  throughout history, classical 1960s, 1970s, 1980s, 1990s, 2000s, early 2010s to 2020s. Computer Vision, Reinforcement Learning, Program Synthesis. Lifelong Learning, Human-Computer Interaction, Mixed Initiative Interfaces; Evolutionary programming, Genetic Algorithms, Self-improving agents; Speech Synthesis, Speech Recognition, Audio Generation etc.  Groundbreaking or important researchers or related to the flow and context of the reviewed topics; and a few Bulgarian researchers who participated in some of the works.

*  Lifelong Learning, Continual Learning, Reinforcement Learning (historical Q-Learning, modern Deep Q-Learning: Atari DeepMind …), RL for LLMs, policy optimizations (DPO, PPO, OREO) … Conditional Random Fields (CRF); Chain-of-Thought prompting …

* Survery of other techniques and research in computer vision,  preceding the explosion of the application of convolutional neural networks after 2012: DBN, RBM, MRF, SIFT etc.

* Survey on Early Deep Learning architectures and Normalizations; seminal papers and PhD theses by pioneers in DL from the schools of LeCun, Hinton, Bengio: M.Ranzato, V.Mnih, A.Krizhevsky, I.Sutskever, A.Mohamed …

*  Survey of Object Recognition and Classification before Deep Learning

* Selected Computer Vision works from 1960s to 2020s

* Exploration and introduction of concepts and techniques in computer vision, machine learning, neural networks

*  Mixed-Initiatve Interaction

*  Audio: Speech Synthesis, Audio Generation, Speech Recognition; 1980s to 2010s

* Neural Machine Translation, Language Models, LLMs, Text Generation, Text and Language Learning and Representation, Word-Embedding

* Alternative approaches for sequence and next words prediction, instead of neural networks: stochastic memorizer, sequence memorizer* Transformers - the seminal paper from 2017

* Tansformer architectures for images and for reducing the quadratic complexity

* Neural Program Synthesis

*  Tansformer architectures for images and for reducing the quadratic complexity

* Evolutionary Algorithms | Genetic Algorithms | Genetic Programming
*  Genetic Programming, Genetic Algorithms, Evolutionary Programming: Part II

* Summary and selection of important concepts in Evolutionary Algorithms | Genetic Algorithms | Genetic Programming etc

*  Vision Transformers – ViT

*  Multimodal Learning, Dialog Learning, Continual Learning

* Diffusion Models

* Self-Improving General Intelligence, Recursive Self Improvement


(...)



Introductory Notes

* Most of the text in this volume of references is in English, with a few small  sections and notes in Bulgarian.

* It is a record of explorations and can serve as a dataset for study, recall and food for thought for curious readers and thinking machines.

* The order and clustering is both thematical and chronological through the literature review study.

* Search for specific topics, names, fields etc. as with the other volumes.

* Why diferent fonts? Diversity. Future versions may be generated from a database core or displayed with Vsy/AI agents and generate different layouts, connections etc.

* In the future it would be operated with the AGI infrastructure Vsy (
Вседържец, Вси) and the Research Accelerator ACS (unpublished yet), which will make it “living”, dynamic, self-extending, translating etc.

* For more Bulgarian and other selected research see also #Anelia #prophets #Listove etc.

* Основно на английски, някои бележки на български. Виж: Лазар Вълков, Боян Александров.

* Изследвания на други методи в компютърното зрение от 1960-те до 2000-те и в навечерието на бума на приложенията на конволюционни невронни мрежи в края на 2012 г.; методи в машинното обучение: DBN, RBM, MRF, SIFT; MSER и др. (…)

(...)

Legend: Cmp: compare. Tosh, T.A., TA, Todor: comments by the author of “The Prophets …”
File: Lazar-…


See also appendices: in English: Universe and Mind 6, “Calculus of Art: …”, …
parts of Listove and Irina; some parts of the main volume; #Anelia – the work of many Bulgarian researchers In English and Bulgarian. E

@Vsy: Systematize, draw diagrams, tables, collect in memory

(...)

0 коментара: