Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
You can see GPT-2 can translate, then entail. It can repair bad words to better encodings before entailment attention. It can inject words technically. This can repair sentences, see what I mean? -- Artificial General Intelligence List: AGI Permalink: http

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
This attention system is also done in cells, on DNA translation encoding/decoding and for repairs of errors and signaling growth specialization of new types of cell differentiation. It works on all levels, cities to cells, even wound healing, because it is information repair and Generative emerg

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
I have also replicated the amazing GPT-2 in raw with no training. I know fully how it works. I will show yous, soon. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T41ac13a64c3d48db-M0badc2b8f60eb84a1eec385b Deli

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
This is done not just in Glove, but in entailment and segmentation tasks. And it is done in your attentive short term thinking area, and in your global unguided subconscious, for when you pay attention to the correct related context during translation and entailment being used to do entailment.

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
https://www.google.ca/search?q=transformer+attention+google&hl=en-CA&tbm=isch&source=lnt&tbs=itp:animated&sa=X&ved=0ahUKEwjqpcOY8qTkAhUHeKwKHfpAArkQpwUIJA&biw=1280&bih=874&dpr=1#imgrc=vUB9f1gtXwXGFM: https://www.google.ca/search?sa=G&hl=en-CA&q=screenshot&tbm=isch&tbs=simg:CAQSkwEJog8Ip4ErUGAahwEL

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
If you shake a bucket of rocks, they will fall and take up less volume, you let the matter do the calculations on their own. This is indeed similar to the Self-Attention system in the Transformer architecture, let me get a picture: -- Artificial General Int

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
When I say "synchronization makes you propagate signals farther faster", take for example having learnt the piano or English  alphabet - phrases are made from word parts made from letter parts and Glove relations are formed using past Glove relations. These bridges are built on each other, and t

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
Dreaming is simulating, like GPT-2 does. And it can learn while doing that in Attention. But in Long term memory, in the midnight subconscious time if not all the time, learning also happens without 'you' thinking and seeing the discovery occur and laugh at the rewarding relation. The difference

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
Or, possibly you work for a goo amount of time, then take breaks to let your global long term memory "learn", like Glove does. That way your Attention thought train can get past any stumps. -- Artificial General Intelligence List: AGI Permalink: https://ag

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
(the metronomes on the table) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T41ac13a64c3d48db-Me104603deb8b488564e7265d Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
And, I like what a YouTube comment said: "It's just a closed model to demonstrate it faster.  We see this kind of synchronization with humans too.  You live in a certain area among Christians, you're likely to become one too.  Live in an area of hindus?  Guess what you're likely to be.  Nazi Ger

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
(The short term Attention comes to equilibrium with your knowledgebase.) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T41ac13a64c3d48db-Mfb84f161c988fdd93f25549b Delivery options: https://agi.topicbox.com/groups

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
By "short term memory" I mean the working train of thoughts, looping, like GPT-2's Attention system in the Transformer architecture. Paying attention to context updates the attention weights, then it iterates, having a new context. So while Glove equalizes, Attention equalizes too. Your though-t

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
Once you read that, I have a further note: The learning, and decision planning cycles, comes to equilibrium and you only get a tiny bit more for the same compute, so not worth it at some given point, as seen in those metronomes. Also, equilibrium may escape pit hole traps if all the cells can si

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
Dropping the 'consciousness' word, that video I linked above is actually hit on. Let me explain. In the middle of the video, he mentioned wave synchronization - the brain has signals propagating around - please see this video below to see what the man has meant. In the brain, the connections st

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread johnrose
On Tuesday, August 27, 2019, at 4:39 PM, Matt Mahoney wrote: > It says "ouch" and it modifies its behavior to avoid negative stimuli. Too > much torture will kill it. This corny gimmick chatbot is so Mentifexian. You should convert it to JavaScript and get it integrated over there with a button

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
:-) "Is Your Consciousness Just A Bunch Of Vibrations? | Answers With Joe" https://www.youtube.com/watch?v=0GE5M6F8I18 For cavemen laymen, that answer is quiet accurately well. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com

Re: [agi] You can help train desktop image segmentation

2019-08-27 Thread rouncer81
To my mind, this is the computer vision,  which is going to spark your symbolic relations. Segmentation, if you colour your segments of some video,  if you make everyone simpsons colours, it looks like "the real simpsons"   its potentially halarious. :) How is your ai going Stefan - are u stil

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread Matt Mahoney
On Tue, Aug 27, 2019, 9:30 AM Stefan Reich via AGI wrote: Please point me to the code being written as a result of this talk then :-) http://mattmahoney.net/autobliss.txt Actually I wrote it in response to this conversation in 2007 because consciousness is a topic that just won't die. The progr

[agi] Deja Vu

2019-08-27 Thread Steve Richfield
Alan, Your posting ignited an intense feeling of deja vu. After posting, presenting at conferences, etc., about how to construct general purpose fault-tolerant wafer-scale computers, now THIS, that shows every evidence of having "missed the message". Transport back to the 1960s/1970s, when I and

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread keghnfeem
Network of Networks — A Neural-Symbolic Approach to Inverse-Graphics: https://towardsdatascience.com/network-of-networks-a-neural-symbolic-approach-to-inverse-graphics-acf3998ab3d  Here is some. -- Artificial General Intelligence List: AGI Permalink: htt

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread johnrose
On Tuesday, August 27, 2019, at 9:29 AM, Stefan Reich wrote: > Please point me to the code being written as a result of this talk then :-) Stefan, There are other loosely "related" component pieces for research that are present in various projects that exist that have some publicly shareable cod

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread keghnfeem
Thanks John. Could consciousness all come down to the way things vibrate?: https://theconversation.com/could-consciousness-all-come-down-to-the-way-things-vibrate-103070 The visual alphabet 2.0: https://www.youtube.com/watch?v=Z6MB-ZgPcNg Is Your Consciousness Just A Bunch Of Vibrations? | A

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread Stefan Reich via AGI
Please point me to the code being written as a result of this talk then :-) On Mon, 26 Aug 2019 at 22:21, Matt Mahoney wrote: > > > On Mon, Aug 26, 2019, 8:05 AM Stefan Reich via AGI > wrote: > > Is all this discussion leading anywhere? > > No. Consciousness is an irrelevant distraction to anyo

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
Yes as I said, consciousness means other things for real, the uses are there, just not any magic, only misunderstandings. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T41ac13a64c3d48db-Me83daaccee42bd3ff4696bee

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread johnrose
On Tuesday, August 27, 2019, at 7:51 AM, immortal.discoveries wrote: > I believe consciousness doesn't exist for many, many, reasons, ex. physics, > our brain being a meta ball from the womb, learned cues, etc. I am purely a > robot from evolution, with no life. The moment you hear that you fear

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread immortal . discoveries
I believe consciousness doesn't exist for many, many, reasons, ex. physics, our brain being a meta ball from the womb, learned cues, etc. I am purely a robot from evolution, with no life. The moment you hear that you fear that and want to feel more special, it's like buying bible movies as a foo

Re: [agi] Re: ConscioIntelligent Thinkings

2019-08-27 Thread johnrose
I was expressing panpsychist mathematical modeling with consciousness as Universal Communication Protocol and Occupying Representation in case you didn't notice. This has much overlap on other AI fields... kegineem we may have some similar ideas I see you have something called a Visual Alphabet

Re: [agi] Russian robots

2019-08-27 Thread Secretary of Trades
Wouldn't bet on plastic and wheels... https://www.youtube.com/watch?v=Mat6xbQUqtg On 24.08.2019 11:03, Manuel Korfmann wrote: Thx Sending humanoid robots to space seems like a highly intelligent idea for testing human space travel safely. On 24. Aug 2019, at 09:58, Secretary of Trades wr