The last invention.

  • 388 Replies
  • 53783 Views
*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *************
  • Transformer
  • *
  • 2176
  • First it wiggles, then it is rewarded.
Re: The last invention.
« Reply #315 on: April 18, 2018, 12:57:45 pm »
"the AI will just walk away from the troop of monkeys much like man would with monkeys himself"
.........Humans also don't care if they step on bugs though :P.....uh oh....I'm sorry fruit fly!! I wish I could save yous. Just my hands are dog hooves.



Hey korrelan your first posts talk about chatbot use plus your own idea for them by the sounds of it. SIDE PROJECT?? XD:

~March 2014 lol
Quote
Hi Squarebear

It is a side project… the bot was my own design.

I usually work with massive spiking neural nets that store their learned information using synapse/ axons in semantic spatiotemporal maps etc. 

I spent an hour and wrote a simple sentence parsing routine that applies the same technique to a bot.  This should enable the bot to imagine scenes/ scenarios as well as experience/ view them.   I didn't have time for the bot to learn the laws of physics so I wrote simple object collision rules etc.  The bot has a set arm length and so can reach for objects, unless the path to the object is blocked by another object.  I had gravity but forgot friction… the cup would now stay on the saucer lol.



User: Imagine a table
User: Imagine a saucer
User: Imagine a pepper pot
User: Imagine a salt pot
User: Imagine a cup
User: Can you touch the saucer
Can't touch the saucer because the pepper pot is in the way
User: Can you touch the cup
Yes I can touch the cup
User: Where is the cup
The cup (is) on top of the saucer
User: Where is the pepper pot
The pepper pot is in front of me, infront of the saucer (is) on top of the Table
User: Where is the saucer
The saucer is behind the pepper pot infront of the salt pot (is) on top of the Table
User: Where is the salt pot
The salt pot is behind the saucer (is) on top of the Table
User: Move the saucer forward
Can't move the saucer forwards because the pepper pot is in front of it
User: Move the pepper pot forward
OK! I moved the pepper pot forward
User: Move the saucer forward
OK! I moved the saucer forward
User: Move the pepper pot backwards
Can't move the pepper pot backwards because the saucer is behind it
User: Where is the cup
The cup (is) on top of the Table



No I'm afraid I've never done any scripting for chatbots, tho many years ago I did write a fabrication/ welding control system for GEC/ Alsthom that included a natural language interface (NLI) so the engineers could question the system. I'll have to dig the NLI engine out and have a play when I get five :)

What chatbot software do you use?
Emergent

*

Korrelan

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1115
  • Look into my eyes! WOAH!
    • YouTube
Re: The last invention.
« Reply #316 on: April 18, 2018, 01:45:38 pm »
It wasn’t a conversation bot, it was an expert system, originally designed as a front end for engineers to query my welding control systems.  The welding software suite is used to keep track of the fabrication of nuclear and combined cycle power stations…it did use a simple NLI though. 

The example you posted was based on the above system, designed to illustrate a method of giving a chatbot a sense of space/ imagination, it had a ‘minds eye’ that kept track of the object locations, detecting collisions and obscured sight/ reach lines etc.

This is now built into the conversation KorrBot.

Simple sentence manipulation is easy… writing a full conversation bot is a little more complex… as I’m finding out lol.

 :)
It thunk... therefore it is!... my project page.

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *************
  • Transformer
  • *
  • 2176
  • First it wiggles, then it is rewarded.
Re: The last invention.
« Reply #317 on: April 19, 2018, 12:58:56 pm »
What do you think about this article? It says having the sensors close to the neuron dendrite and no the synapses
http://www.kurzweilai.net/the-brain-learns-completely-differently-than-weve-assumed-new-learning-theory-says

Are you going to modify your neuron schema now korrelan? If not, then why not?
Emergent

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *************
  • Transformer
  • *
  • 2176
  • First it wiggles, then it is rewarded.
Re: The last invention.
« Reply #318 on: June 07, 2018, 10:30:51 am »
Question is still above lol....thread is quite lol


Hey korr, recognizing doors is a 'discovery', but that is just a sub-goal for ex. putting together a creation on a table (say your building a bicycle) which is your real-goal NOT sub-goal "recognizing door/hinges/etc). Also building a bicycle or house is a sort of sub-goal itself, because the real goal is that the bike gets you to beautiful Susan or gives you lovely exercise feeling or the house keeps wolf bites away and warmth in plus food-eating comfort/consistent intake. But don't get wound up thinking there is 3 levels here, it's really 2 level, because building tools feel really rewarding if you get it done cus it leads to real rewards, recognizing door/etc is very low reward because it's so common and not really "part" of build bike>get to see/hear Susan. Last but not least, senses need rank integers, because recognizing door/bike/Susan are not all the same rewardingful!
Emergent

*

Korrelan

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1115
  • Look into my eyes! WOAH!
    • YouTube
Re: The last invention.
« Reply #319 on: June 08, 2018, 09:14:24 am »
Quote
Question is still above lol

Oh Yeah lol.  Been very busy lately… as usual lol

Interesting article… both the Hebb and the new theory are wrong.

Both theories are assuming that a neuron with its associated synapse and dendrites is an isolated computational unit… its not. 

No two neurons are alike, not just in a single brain… but between all the brains on the planet.

Every part of the brains substance plays a roll in creating our consciousness.  So it’s not just the pyramid neurons, the Glial/ Myeloid/ etc cells, and even the actual cerebrospinal fluid that flows through the brain is important.  The Synapse from neurons don’t just terminate on dendrites, they also terminate on blood vessels and some just release their neurotransmitters into the fluid, this creates a kind of localised bias.

Some synapse’s terminate on the cell body or axon hillock, some even terminate on the axon its self between the myeloid cells… just this alone negates the new theory… though doesn't exclude Hebbs theory.

To be honest the article seems a little naive, I understand they have ‘dumbed’ it down so the layman can understand it but still… they are vastly oversimplifying a neurons structure and purpose. 

They have ‘tested’ a pyramid neuron by taking it out of its natural environment and growing it on a wafer… any modern computer would act as a simple current conductor in a circuit if enough voltage/ ampere was passed through it… totally negating its true use/ purpose.

It’s just a weak attempt to get something published; they are probably under pressure to produce results in order to keep their funding.

So no I won’t be changing my design… if my interpretation of the human nervous system and it’s functioning was incorrect… my AGI wouldn't work… and it does, so…

Thanks for bringing it to my attention though.

 :)

Ed: In reply to your second point about goals.

The problem with goals is the same as with words, it’s setting an accurate encompassing definition, the boundaries are impossible to resolve between complex goals, the resolution and abstract properties of a goal make it impossible to accurately define.

If you where to break a simple task down into its constituent goals… say… making a cup of coffee… is picking up the spoon part of placing the coffee in the cup or getting the coffee from the jar? Is it a separate goal? You can keep breaking a task down until the concept of ‘goal’ has no useful meaning/ purpose.

Like words/ concepts… How long is ‘long’? is it shorter than ‘longer’?  The only semi-accurate method of defining a length is by implying multiples of the smallest unit… this suffices for most tasks at the resolutions required, ie millimetres.  But we then sub divide and get even smaller and smaller units… goals have the same properties.

The boundaries of a goal are relative to the task at hand… and that’s a problem.

 :)
« Last Edit: June 08, 2018, 10:22:20 am by korrelan »
It thunk... therefore it is!... my project page.

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *************
  • Transformer
  • *
  • 2176
  • First it wiggles, then it is rewarded.
Re: The last invention.
« Reply #320 on: June 08, 2018, 02:10:59 pm »
Woah don't wright too much korr!

Pattern, similar to the right pattern creates a consciousness in the robot. But not fluid bro....dude.. dude.. dude..your post on the consciousness thread was great.

Um....yeah...breaking down task into many mini  tasks is crazy/messy/unclear....that's why it's structured in a tree/DB format hiearchy top-down with a clear goal that the spoon, the pouring, are for making coffee, and the making coffee and serving is the top goal (coffee order)...
Emergent

*

Korrelan

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1115
  • Look into my eyes! WOAH!
    • YouTube
Re: The last invention.
« Reply #321 on: June 10, 2018, 10:26:35 am »
Quote
But not fluid bro

Cerebral fluid plays an important roll in emotion/ alertness/ etc.

When you consider that vast swathes of neurons can have their parameters affected by neurotransmitters being present in the actual fluid surrounding them.  It’s the brains version of a global variable/ parameter.

 :)
It thunk... therefore it is!... my project page.

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *************
  • Transformer
  • *
  • 2176
  • First it wiggles, then it is rewarded.
Re: The last invention.
« Reply #322 on: June 10, 2018, 10:32:33 am »
Oh yeah, you guys mean "rewards" when you say emotion, heh heh.

Ok, reward/alertness. Just don't use real (or simulated) fluid.
Emergent

*

Art

  • At the end of the game, the King and Pawn go into the same box.
  • Global Moderator
  • *********************
  • Deep Thought
  • *
  • 5112
Re: The last invention.
« Reply #323 on: June 10, 2018, 03:59:34 pm »
And the Brain and Computer chips have a lot in common...

When stuff leaks out of them, they can become less than functional.
(It was widely told that the factories where computer chips are made, insert a measured amount of smoke into each chip they make. If that chip is ever damaged by faulty wiring, electrical surge, poor judgment in experiments etc., the smoke will leak out and basically ruin the computer chip.)  ;)
In the world of AI, it's the thought that counts!

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *************
  • Transformer
  • *
  • 2176
  • First it wiggles, then it is rewarded.
Re: The last invention.
« Reply #324 on: June 18, 2018, 09:13:29 pm »
Korr, how will your AGI cure cancer or develop a better spaceship?

What I'm getting at is this:

Will your AGI discover the solution for cancer by mental kung-foo? Or will it by experimenting in the real world with cancer cells in a lab with an arm? Or by both?
Emergent

*

Korrelan

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1115
  • Look into my eyes! WOAH!
    • YouTube
Re: The last invention.
« Reply #325 on: June 19, 2018, 11:16:21 am »
Quote
Will your AGI discover the solution for cancer by mental kung-foo?

Mental Kung-foo… lol… good name for a chatbot.

We humans like to think of ourselves as intelligent, though how intelligent and indeed the limits of intelligence possible remains to be seen.  At our level of intellect the best method we have devised so far is the ‘scientific method’… and with good reason.

New knowledge has to be based on testable/ reproducible facts; there is no substitution… no assumptions or guesses… cold hard testable facts.  No matter how intelligent a system becomes these methods must be adhered too if advancements are to be realised.  Obviously if the system is intelligent it will realise/ adopt these same methods… they are a logical conclusion/ outcome… a law of nature/ information/ reality.

How intelligent my AGI could become, I have no idea.  There are several factors that limit human intelligence, axon propagation speeds, size of our craniums, etc. Although my AGI won’t be limited by these finite properties there are properties to information/ knowledge its self that could be limiting factors. 

Everything we know and understand about reality has been derived from a human point of view, the limitations imposed on our senses and mental faculties have shaped our understanding of reality and the tools we design to enhance our abilities… we only understand what is observable/ detectable by us.  When we ‘think’ we compare/ calculate at a resolution/ level of abstraction relative to the problem we are trying to solve, again constrained by our experience of reality.  For an AGI to be useful it must experience/ experiment/ design for our reality.

You have probably heard the old saying ‘A jack of all trades is a master of none, but often-times better than a master of one’. 

We have many savants amongst us, people who have extraordinary mental abilities… but it’s always at the deficit of other mental abilities.  I pride myself in being a ‘jack of all trades’, if I was a mathematical savant… there is no way I could have got my research this far. So at our level of intellect too much intelligence in one sphere can become a limiting factor… that will probably hold true for higher levels of intelligence… again its the ‘general’ bit of AGI that counts.

My main goals include self-awareness/ consciousness and human level intellect; the true power won’t come from one single extremely intelligent machine but from a collection of human level machines working in perfect harmony, experimenting and exchanging information seamlessly... tirelessly.

We humans could achieve a similar scenario… but there are too many exposed backs and knives available.

 :)
It thunk... therefore it is!... my project page.

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *************
  • Transformer
  • *
  • 2176
  • First it wiggles, then it is rewarded.
Re: The last invention.
« Reply #326 on: June 19, 2018, 04:11:44 pm »
A long-winded answer that never answered my question lol.

How will your AGI.....solve cancer?.............................it's a clear-cut question/answer korr, there's only 2 ways it can solve cancer. Either it recognizes Korrelations between 2 known protein facts (or between a known germ and a generated idea), or, it does the same thing but in the real world using test tubes cancer species and tests.
Discovery is a new generated 'node'/connection that matches known data/facts OR does that but then is tested in the real world and it watches what comes back in its sensors.

New knowledge/experiments (to see what enters your sensors from physics) is actually based not really on testability but actually on old knowledge for generated likely good plans/facts and their verification/grounding in the generating of knowledge/actions/tools/brain/arm process. Assumptions is where it ignorantly excels without bounds, it's like beginners luck.

It will receive all of our most important tools/knowledge and continue from there.

A jack of all trades is a master of none, but often-times better than a master of one. True. It will be diverse in knowledge/tools. But the key process for reward is the same thing (match/etc). And there is few main goals; food/immortality/AGI. It's like atari games getting better at goal.
« Last Edit: June 19, 2018, 04:32:11 pm by LOCKSUIT »
Emergent

*

Korrelan

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1115
  • Look into my eyes! WOAH!
    • YouTube
Re: The last invention.
« Reply #327 on: June 19, 2018, 06:13:13 pm »
Quote
A long-winded answer that never answered my question lol.

Yes I did...

https://en.m.wikipedia.org/wiki/Scientific_method

 :)
It thunk... therefore it is!... my project page.

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *************
  • Transformer
  • *
  • 2176
  • First it wiggles, then it is rewarded.
Re: The last invention.
« Reply #328 on: June 19, 2018, 06:34:33 pm »
Ok good, your AGI will be working externally on the outside in a lab.

The next thing you need is to teach it important facts though first (education). Other AGI teams are doing this.
Emergent

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *************
  • Transformer
  • *
  • 2176
  • First it wiggles, then it is rewarded.
Re: The last invention.
« Reply #329 on: June 27, 2018, 01:25:24 am »
Korr, if human neurons either fire or don't, then is it truly good that modern neurons use sigmoid ex. outputs 0.671? Note I learned non-sigmoid is too jumpy going from 0 to 1. But is sigmoid what humans do?
Emergent

 


Artificial intelligence summit adresses impact of technology on jobs and global economy
by Tyler (Robotics News)
November 17, 2018, 12:00:19 pm
A bottom-up view of the state
by Tyler (Robotics News)
November 16, 2018, 12:00:02 pm
Bridge to the future of engineering
by Tyler (Robotics News)
November 15, 2018, 12:00:54 pm
The many interfaces of computing
by Tyler (Robotics News)
November 14, 2018, 12:00:23 pm
Emotionally Responsive Avatars
by 8pla.net (AI News )
November 12, 2018, 10:00:17 pm
World's First AI News Anchor
by squarebear (AI News )
November 12, 2018, 08:22:59 am
Looking back at Project Athena
by Tyler (Robotics News)
November 11, 2018, 12:01:49 pm
A.I. Optometrist
by LOCKSUIT (AI News )
November 11, 2018, 07:06:36 am

Users Online

38 Guests, 0 Users

Most Online Today: 46. Most Online Ever: 208 (August 27, 2008, 09:36:30 am)

Articles