Re: [agi] John Carmack raises $20M to develop AGI

The 16 minutes out of the 5 hours that he speaks about AGI are here; https://www.youtube.com/watch?v=xLi83prR5fg -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T5bbfadf63743faf7-Mf3e51f60d8833f08cbb9eeff Delivery

Re: [agi] The next advance over transformer models

Hi Rob,  I have no idea.  I read about blending a year or so ago but have not studied Howarth's work in any detail to be able to answer your question. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T5d6fde768988c

Re: [agi] The next advance over transformer models

If you are looking for a hierarchical structure which reuses simpler parts (letters, words, phrases) in compositions that include overlaps to represent more complex things (words, phrases, sentences) you might want to have a look at binons.  http://www.adaptroninc.com/BasicPage/presentations-and

[agi] Symbolic Neural Networks for Perception

Here is a paper titled "A Grounded Deep Symbolic Neural Network for Perception" that I am planning to submit to the NeSy 2022 workshop. It is one of a number of workshops in the Second International Conference on Learning and Reasoning (IJCLR 2022) in Windsor, UK on 28th – 30th September. Papers a

[agi] Presentation to Northwest AGI Forum

Last Sunday I gave the following presentation to the Northwest AGI Forum. Grounding Invariant Features with Binons for Perceptual Constancy Both animals and artificial intelligent agents rely upon the representation of invariant features of objects and events for perceptual constancy during re

[agi] Re: AGI in the news

A little research shows that: Sanctuary AI is an artificial general intelligence company founded in January 2018, and is based in Vancouver, B.C. Sanctuary's mission is to build synthetic humans – “synths” – that are indistinguishable from us physically, cognitively and emotionally. The company

[agi] Re: AGI requirements and the Adaptron cognitive architecture - new presentations

Wikipedia provides a reasonably easy to read description of the forward and inverse models in action control.  https://en.wikipedia.org/wiki/Internal_model_(motor_control) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/gro

[agi] Re: AGI requirements and the Adaptron cognitive architecture - new presentations

Thanks for your question. First the diagram is not meant to illustrate the exact links between the hierarchies. It is meant to illustrate that control binons (nodes) are needed between percepts and acts. One type of control binon connects percepts to acts such that if the action habit is active

[agi] AGI requirements and the Adaptron cognitive architecture - new presentations

There are two new presentations about the Adaptron cognitive architecture. One is on requirements for AGI and the other is on its software architecture. They are at: http://www.adaptroninc.com/BasicPage/presentations-and-slides   -- Artificial General I

[agi] Re: Sustainable Mountain-Based Health and Wellness Tourist Destinations: The Interrelationships between Tourists’ Satisfaction, Behavioral Intentions, and Competitiveness

Is there an AGI topicbox administrator who can delete this? -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T3389d065100463ce-M7a3c83316a2ec1672a2d63d7 Delivery options: https://agi.topicbox.com/groups/agi/subscrip

Re: [agi] All Compression is Lossy, More or Less

Hi Matt,  That is a great concise description of the use of lossy versus lossless compression in AGI. But in your second paragraph, I believe you meant to say that  - _Lossless_ compression can only test deterministic predictors ...  All the best, Brett  -

Re: [agi] Re: Ideas Have to Act on Other Kinds of Ideas

Improved Introduction to Adaptron and binons:  http://www.adaptroninc.com/sites/default/files/inline-files/Adaptron_and_Binary_Neurons_-_Introduction_V11.pdf -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T1675e04

Re: [agi] Re: Ideas Have to Act on Other Kinds of Ideas

Hi IM, You and I have different visions of what is an AGI. For you it is software that intelligently processes text, searches for patterns and can generate and communicate text.  For me it is a baby, embodied with sensors and actuators that learns everything from the ground up. It takes many yea

Re: [agi] Re: Ideas Have to Act on Other Kinds of Ideas

Thanks Jim, Good question.  I have improved the wording in my book draft. "...as it learns, it builds up integrated perception–action hierarchies of binons to represent its experiences." -- Artificial General Intelligence List: AGI Permalink: https://agi.t

Re: [agi] Re: Ideas Have to Act on Other Kinds of Ideas

No, knowledge is stored in many hierarchies but they are all built from the same lowest level binons which represent the sensor readings (it is grounded). The lowest level binons are reused / shared by many higher level binons so from a bottom-up perspective you have all sorts of different trees

Re: [agi] Re: Ideas Have to Act on Other Kinds of Ideas

Jim, If you think chatting about your algorithm would help, I am available to chat over zoom. I have a M.Sc. in computer science and have been programming algorithms for 53 years and I teach software engineering courses for Learning Tree International.  Cheers Brett -

[agi] Re: Ideas Have to Act on Other Kinds of Ideas

It is always easier to ask questions than read a detailed description, try to understand it and compare it with ones own work or others. The work is being done by the person who has to answer the questions. In this case I suggest the work be done by the questioner.  I have already spent numerous

[agi] Re: Ideas Have to Act on Other Kinds of Ideas

Hi Jim, It has been 2 years since we last communicated. The article I was writing has now turned into a book and based on your continued AGI curiosity and search for answers as illustrated in this thread I invite you to read the introduction to my book. Most of the chapters are now complete and

[agi] Re: Conference link

viewform?usp=mail_form_link> Here's what was received. AGI-21 Registration Email List Email * br...@adaptroninc.com Name: * Brett N Martensen What date(s) do you wish to attend? * ✓Friday 15 October 2021 ✓Saturday 16 October 2021 ✓Sunday 17 October 2021 ✓Monday 18 October 2021 Are you (chec

[agi] AGI 2021 Conference registration for free

The AGI 2021 Conference starts on Friday 15th Oct. Registration as an attendee is free. http://agi-conf.org/2021/registration/ -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf91660db54acabc1-M68e5b93a5fc5a0d330

Re: [agi] UNDERSTANDING -- Part I -- the Survey, online discussion: Sunday 10 a.m. Pacific Time, evening in Europe, you are invited

Hi Boris,  the term "true" is used in the given sentence to be a property of some fact in the model. Having a true belief about something is a  measure of  your certainty about the facts in the model. So a true belief is a fact about something in the model (usually a relationship) that  you are

Re: [agi] UNDERSTANDING -- Part I -- the Survey, online discussion: Sunday 10 a.m. Pacific Time, evening in Europe, you are invited

I have read through all the definitions and have compiled a new definition that I would like to use. It is based on a definition that can be used to help construct an AGI because it describes key properties of what understanding is comprised. Noun: As a thing: An understanding is a model of s

[agi] Re: Gazelle financing Attempt 2

Spend it wisely :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T1236f770cf202ee3-M4205d431bea0c184c61cf4d0 Delivery options: https://agi.topicbox.com/groups/agi/subscription

[agi] Re: Gazelle financing Attempt 2

0.786 ETH sent -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T1236f770cf202ee3-M64640db547a1fa42ca006860 Delivery options: https://agi.topicbox.com/groups/agi/subscription

[agi] Re: Gazelle financing Attempt 2

Hi Stefan, I have faith in you. Provide me with an Ethereum address and I will send you the equivalent of 2K Euro. You better quickly convert it into Euros because you have no idea where the price will go.  Cheers, Brett -- Artificial General Intelligence

Re: [agi] How does a machine "understand"? What is your definition of "understanding" for an AGI?

Gadi Singer, VP of Intel Labs, who leads their cognitive computing research has a definition of understanding at 16:00 minutes into his recent video presentation. https://www.youtube.com/watch?v=aqfizAySe0E&t=1538s The video is worth listening to all the way through. -

[agi] The road to AGI cannot be accomplished via text alone

Mykola Rabchevsky, in his short post, does a fine job of describing why to accomplish anything close to human level intelligence and communication, text must be grounded. There are too many short-sighted projects in development that think the road to general-purpose artificial intelligence is th

Re: [agi] Feast Your Qualia on this One

Do you have any references to papers that prove "All motor actions of a robot can be controlled by predictions"?  Or have you been able to prove this or  show this fact from your research? If you feel this is self evident please explain it because it is not obvious to me.  --

Re: [agi] Spammed With 16 YouTube Videos From the Computer History Museum "Honoring Raj Reddy"

One of IBM's earlier machines:   https://commons.wikimedia.org/wiki/File:IBM_Cheese_Slicer_(11595561416).jpg -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T36c6d508ad4d7749-M7b360295dd37a3cceae3dbe7 Delivery opt

[agi] Opportunity to review my AGI book

As a fellow AGI researcher I would appreciate your review of my AGI book. If you are interested, I will provide you with a draft version, one chapter at a time, approximately two months apart. The book currently has 10 chapters. There is an abstract of the book on my website: http://www.adaptro

[agi] Re: AGI Conference 2021?

Try this: https://waset.org/artificial-general-intelligence-conference-in-june-2021-in-tokyo -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T05f9e3871800e2db-M76f9fc7033e2b92e955a7eaf Delivery options: https://ag

[agi] Re: Cyc's application problem

The heart of the problem with Cyc is it's not grounded. It is therefore hard for it to achieve true AGI status. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Te3966330b8b36194-M110591028152612a21b5c3b8 Delivery

Re: [agi] Who wants free cash for the support of AGI creation?

I'm going to be leaving this group because of the language used by rouncer81. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T26a5f8008aa0b4f8-M5be9683ea3a81eb69b9cbb20 Delivery options: https://agi.topicbox.com/g

[agi] Re: putting models in your robots head

You should read this -   Building Machines That Learn and Think Like People    by Lake, B. M. et al http://web.stanford.edu/class/psych209/Readings/LakeEtAlBBS.pdf pages 16-19  Section 4.1.1 Intuitive physics -- Artificial General Intelligence List: AGI Per

Re: [agi] COMPUTE THIS!!!

Time for some studying: Read: https://en.wikipedia.org/wiki/Language_of_thought_hypothesis And: https://schneiderwebsite.com/uploads/8/3/7/5/83756330/lot_for_the-routledge-companion-to-philosophy-of-psychology.pdf -- Artificial General Intelligence List

[agi] Re: MindForth is not a game.

Hi Arthur,  Your wikipedia link is not working. Cheers Brett -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T3ae4274321f1333c-Mffc39c3d642ca4f3cc96e33c Delivery options: https://agi.topicbox.com/groups/agi/subscri

Re: [agi] Whats everyones goal here?

Good thinking. Binons are reused / shared by many target nodes. Its a compositional hierarchy top down but a lattice or heterarchy from bottom up. http://www.adaptroninc.com/sites/default/files/inline-files/Binons%20V1.pdf and  http://www.adaptroninc.com/sites/default/files/inline-files/Hierarchi

Re: [agi] Whats everyones goal here?

A lot more storage - yes. Not necessarily a lot more computation. But there are other requirements that also need to be addressed. A few that come to mind are: - Transparency / Explain-ability - Susceptibility to catastrophic interference - Ability to represent hierarchies of actions as well as pe

Re: [agi] Whats everyones goal here?

BASIC - it stands for   Beginner's All-purpose Symbolic Instruction Code. I think we should change it to   Binon Artificial Super Intelligence Code  :)  :)  :)  And Binons (Binary Neurons) - feedforward, deterministic and no weights on the links. If errors occur then new binons are created to r

Re: [agi] Whats everyones goal here?

To put the G back into AI. To develop software (named Adaptron) that allows a robot to learn, think and act autonomously.  Given any configuration of senses and action devices, to learn from experiences (unsupervised). To start with no knowledge except of its goal(s) and how its senses and acti

Re: [agi] Genetic evolution of logic rules experiment

Matt is right - Logic needs to be grounded on experiences.  http://matt.colorado.edu/teaching/highcog/readings/b8.pdf -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T77af318d4abfa8a8-Mf5918de07e97143626ca339f De

[agi] Re: Does anyone here have any recommendations for how to go about obtaining a computer science/programming certification outside of college? What organizations are the best to get one’s certific

Learning Tree has a number of IT certifications. But their courses cost money and they don't have any beginner classes for people who are new to computer science.   https://www.learningtree.com/ -- Artificial General Intelligence List: AGI Permalink: htt

Re: [agi] Re: ConscioIntelligent Thinkings

*Intelligence* has been defined in many ways, including: the capacity for logic , understanding , self-awareness , learning , e

Re: [agi] Complexity - General Learning

Jim, You are right on the money! It's called transfer learning and comes from having generalization in a compositional hierarchy  in which more complex things are composition of simpler but more general things. And the lowest level simplest things yet most general are the stimuli that come from

Re: [agi] My paper in AGI-19

All the papers can be found at: http://agi-conf.org/2019/schedule/ Here is yours: http://agi-conf.org/2019/wp-content/uploads/2019/07/paper_21.pdf -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf27122c71ce3b24

Re: [agi] Re: A mathematics of concpetual relations?

What you are discussing is neural coding mechanisms. As you are aware spiking approaches use spike timing and spiking rates as one idea. I have another idea. A neuron fires as a result of the sum of the number of exciting synaptic connections minus the number of inhibitor connections exceeding a

Re: [agi] Re: salam

Is there an administrator who can delete all this garbage and kick salam out? -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T1655a7a13b5657c3-M4a4a4c425db388a4fbe2f33e Delivery options: https://agi.topicbox.com/g

Re: [agi] Re: A mathematics of concpetual relations?

The database just needs to be able to grow as it learns new things. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T395236743964cb4b-Mfa4233300a6e7ff8aa21045a Delivery options: https://agi.topicbox.com/groups/agi/

Re: [agi] Re: A mathematics of concpetual relations?

Hi Jim,  I've been following this discussion with interest. Good stuff.  If you are looking for a way of representing those millions of bits and only use a small part of it at a time and build it hierarchically may I suggest you look into binons.  In the presentations on binons and the presentat

Re: [agi] AI Game Plan

I'm here. Watching and waiting for something interesting that is explained well and contributes to the building of AGI. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T8e8cca32050f13ab-M2770a2d1f9b9671dcd887517 D

Re: [agi] How do I leave the group?

A subject as challenging as AGI needs people who think "outside the box".  Some are just further outside the box than others. :)  :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf6cd9fbea2c00aa0-Md5f0f9fceb3ee