Ai Dreams Forum
Artificial Intelligence => General AI Discussion => Topic started by: LOCKSUIT on December 12, 2016, 05:00:09 pm
-
Remember back to the famous robot that learns to hop, and improves.
Yous obviously understand how.
But how do you imagine the machine/algorithm?
In a bad poor way?
Or like this?
http://advancessss.deviantart.com/art/New-Canvas-650853524?ga_submit_new=10%253A1481560495 (http://advancessss.deviantart.com/art/New-Canvas-650853524?ga_submit_new=10%253A1481560495)
Is this what you see? Or have you been seeing it as code in a crazy vertical fashion? That would fog your view of AI. To advance greatly means to clearly see it ALL!
In fact, korrelan, kei, and freddy, I advise you to create a very neat and colored-in schematic of your AI. I was astounded once I started to see all my writing as vision of a single small image. Without a image, you are very far behind from where I am. It's a must have.
-
Do any of my advanced AI men here have a image showing neatly most or all of your AI?
I would also really like to hear Art's/korrelan's/etc's reply to the visualization above I originally asked about too, you can see a example in the link.
-
Sorry for not responding sooner Locksuit.
You have it structured so that:
Input = Reward > Sense > Action = Output
Input = Generating > Action = Output
Input = Sense (sensor) > Action = Output
Input = Action > Output (bypassing other parameters like Sense, Reward, Generate)
Much like a condition / response - think Pavlov's Dog...bell ring > salivate
Simple but Interesting drawing
At least this is my observation.
-
The way the blue image I drew works is like this:
1) Input, goes to Generator, to Action, to Output.
2) Input, goes to Reward, to Sense, to Action, to Output.
This allows it go generate and learn actions, then select senses and use actions.
-
As usual you left out the most important part. The part with the magic in it.
-
You mean the sensing ghost the machine creates unto the universe?
Or CNN?
Just trying to help you guys cus I know you's don't have a neat schematic and can't see your AI all that easily.
-
Just trying to help you guys cus I know you's don't have a neat schematic and can't see your AI all that easily.
You don't know that at all. I use graphviz to automatically generate schematics from my work. Instead of wasting time like a bunch of schoolies competing to draw the meanest looking spaceship, some of us are actually doing something useful with our time.
-
Decomposing Tasks like Humans: Scaling Reinforcement Learning By Separation of Concerns:
http://www.maluuba.com/blog/2016/12/9/improving-scalability-of-reinforcement-learning-by-separation-of-concerns (http://www.maluuba.com/blog/2016/12/9/improving-scalability-of-reinforcement-learning-by-separation-of-concerns)
-
Decomposing Tasks like Humans: Scaling Reinforcement Learning By Separation of Concerns:
http://www.maluuba.com/blog/2016/12/9/improving-scalability-of-reinforcement-learning-by-separation-of-concerns (http://www.maluuba.com/blog/2016/12/9/improving-scalability-of-reinforcement-learning-by-separation-of-concerns)
This is just a rehash of the subsumption architecture which has been used in robotics for decades. I wonder what else they're trying to reinvent because they haven't done their research.
https://en.wikipedia.org/wiki/Subsumption_architecture (https://en.wikipedia.org/wiki/Subsumption_architecture)
-
Show me your image of your AI then.
I bet it is not as organized as it could be.
There is no program that will organize something particularly right for the specific project. Things don't work like that. That's like saying you have text, and it knows from the text that the BEST way to place the units is like this cus um er LOOOOOL. That itself is intelligence. Graphviz can't do it for you.
-
Decomposing Tasks like Humans: Scaling Reinforcement Learning By Separation of Concerns:
http://www.maluuba.com/blog/2016/12/9/improving-scalability-of-reinforcement-learning-by-separation-of-concerns (http://www.maluuba.com/blog/2016/12/9/improving-scalability-of-reinforcement-learning-by-separation-of-concerns)
Isn't that what Beethoven is doing?
Decomposing! :2funny:
-
When you understand AI is that blue pic I drew how you see it? Or do you see code/neural-connections? Or hear words and no image visualized?
When you think about how the famous stick-creatures learn to run, is the blue picture I drew basically what you see? Or code/neurons/words.
-
http://www.adampease.org/OP/images/SUMOclasses.gif (http://www.adampease.org/OP/images/SUMOclasses.gif)
-
Who made that?
-
Who made that?
You're kidding me. Can't you figure it out from the URL?
-
Eh.
Yes http://www.adampease.org/ (http://www.adampease.org/)
But why show me it? There is many different sorts of AI schematics/table-sheets on the internet. There's no system in this picture. It is very messy and has 0 mechanical structure. Most of the things can be done by a few things. Others are the body. A better pic could be made.
-
But why show me it?
Can't you figure that out either?
Most chatbots maintain a better of illusion of intelligence than you do.
-
I'm used to links to pictures that are simply on a hosting website, I didn't expect the SUMO one to be on the creators website hence not checking the address bar.
This thread is about "seeing AI" as a "system", the picture you're showing me is a bunch of words, and if it wasn't words it would be not unified/disorganized. My black spaceship picture has very few parts/main parts and is extremely organized.
-
Your ideas are about as sophisticated as a not very bright preschooler's and your ridiculous drawings only serve to illustrate that. If you were a bit more grown up you would have a better grasp of the complexity of the real world and you wouldn't have to grossly oversimplify it in your efforts to cope with it.
If you really want to make a contribution you should start by learning to dress yourself and cook your own meals. Once you've mastered the basics of personal hygiene, then maybe you could start learning to program. I mean really learn, not just pretend like you have been. Then maybe you'll have a contribution to make.
-
I do dress myself and cook my own meals including cakes!
Not programming something doesn't mean I don't have a massive contribution in the making.
-
I do dress myself and cook my own meals including cakes!
Well that's great if it's true and I'm sorry if I seem a bit harsh but it's because I think you have potential. You're full of ideas, but everything you've done so far is hopelessly naive and you need to try a lot harder. Ideas by themselves are worthless, it takes a lot of work, more than you can imagine, to make them into something valuable.
Not programming something doesn't mean I don't have a massive contribution in the making.
That's true, but it is unreasonable of you to expect anyone to believe you without proof. We are all eagerly awaiting that proof and only working software will be enough. Even that video that you've been promising to make won't constitute proof, even if you manage to persuade us to be more patient with it.
I have a lot of patience. I've spent tens of thousands of hours over several decades developing a massive body of sophisticated software that does useful things like parsing and reasoning and language processing on a large scale. It's incredibly powerful software but it's still not AI, it's just a part of it. But because I know firsthand how much work it takes to achieve anything, I have no patience with anyone who has done nothing and is yet to demonstrate that they're capable of anything, yet proclaims loudly how they've solved all the problems that the best minds on earth have yet to solve after sixty years of unstinting effort.
-
I hear you and understand you.
It's pretty cool to hear you and korrelan are "big guys".
I personally have attempted programming and learned c++ and made a note on how to quickly re-learn it if need be. But I got stuck in dead mud on putting it in a robot with that OpenCV. In the end I realize humans haven't yet made it nice here, EV3 programming is beautiful with visual-blocks etc! Got that working. And would pay for it to be made into a full blown tool just for me.
That's why I'm doing everything I can hard to find how to get what I know to others and get our AI tech up to date, if not almost make AI. I've got really mind blowing things up my sleeve, actually expect worlds to appear soon.
-
I personally have attempted programming and learned c++ and made a note on how to quickly re-learn it if need be. But I got stuck in dead mud on putting it in a robot with that OpenCV. In the end I realize humans haven't yet made it nice here, EV3 programming is beautiful with visual-blocks etc! Got that working. And would pay for it to be made into a full blown tool just for me.
C++ isn't a good language to start with or finish with. I spent nearly 10 years programming with C++ and stopped using it decades ago. Unfortunately it makes things too complicated and engineers end up spending more time wrestling with the language than refining their solutions. I mastered C++ and then abandoned it.
A good path for learning is to start out with Python but it's not a good language to use for serious projects because it does not enforce enough discipline. If you are good at making cakes then you know that baking requires a lot more discipline than other kinds of cooking, so maybe you'll be good at programming one day too, because discipline is essential for the really big projects like AI. Once you've mastered Python you might not need anything else, but it would still be good to learn lots of other languages anyway because they have radically different ways of solving problems. You should definitely learn SQL simply because it's so useful.
If you would like to try a professional grade development environment like EV3 then I'd suggest you take a look at MatLab. It is the same kind of thing but rugged enough to cope with industrial and scientific applications.
https://www.mathworks.com/products/matlab.html (https://www.mathworks.com/products/matlab.html)
That's why I'm doing everything I can hard to find how to get what I know to others and get our AI tech up to date, if not almost make AI. I've got really mind blowing things up my sleeve, actually expect worlds to appear soon.
You should consider this quote from Socrates and think about how it applies to you right now.
I know that I know nothing
-
I know that I know nothing
You don't know that.
-
See how intense I go:
http://advancessss.deviantart.com/art/Sumo-651775995?ga_submit_new=10%253A1482013193 (http://advancessss.deviantart.com/art/Sumo-651775995?ga_submit_new=10%253A1482013193)
I'll erase and un-erase many times. All over again shall we?
IM CRAZYYYYYYYYYYYY
-
See how intense I go:
http://advancessss.deviantart.com/art/Sumo-651775995?ga_submit_new=10%253A1482013193 (http://advancessss.deviantart.com/art/Sumo-651775995?ga_submit_new=10%253A1482013193)
I'll erase and un-erase many times. All over again shall we?
IM CRAZYYYYYYYYYYYY
What even is that?
It looks completely disorganized...
-
It's the picture infurl linked to me. See it full here:
http://www.adampease.org/OP/images/SUMOclasses.gif (http://www.adampease.org/OP/images/SUMOclasses.gif)
See infurl, as kei just said - "it looks completely disorganized".
ROFL
-
Why did you erase that and made it appeared to be disorganized?
You imbecile! *sarcasm*
...
Listen, kids.
Never judge too early, or judge too late.
Here I am, I shall slam my head into a wall in a moment.
All are welcomed to watch.
Edit: Oh, I can't do it, I will have Jake to help me.
(https://media.giphy.com/media/SXgG5zHruTjI4/giphy.gif)
*Head smashing sfx*
(https://media.giphy.com/media/12m6YBQBVVPMK4/giphy.gif)
Jake: "You are welcome."
...
Jokes aside...
-
My screenshot showed me in a editor with an eraser clearly having erased it........
But yeah this thing is poorly organized in multiple ways.
1. It's soooo long in hieght and hard to zoom in/out when if wasn't would require less adjustment and more view power.
2. Rotated 90 degrees it would fit better even on my non-widescreen monitor.
3. All jumbled together. Crooked lines. Etc. No spaces. No real/true hierarchy. Fake realistic terms.
I am so packed with secret knowledge it's incredible, I got how to make super metaloid beings, end universes, timetravel back to retry a experiment, etc.
-
You really haven't got the slightest idea what you're looking at have you. Not that it will mean anything to you, but it's the class hierarchy of the Suggested Upper Merged Ontology. It defines an initial framework for all the knowledge in a brain.
This is just one simple aspect of a detailed logical description of the more abstract parts of the world that forms a framework for human intelligence. Common sense in other words. It is a model of the real working software that must stand at the centre of any genuine artificial intelligence software. It doesn't have to be SUMO, it could be CYC or something similar (which is orders of magnitude more comprehensive by the way), but take it or any part of it away and you will have nothing left but the intelligence of an insect. It is complete and correct because it is extracted directly from real working software.
If it's too complicated for you to understand, that's your problem. Erasing parts of it won't make the problem that this software solves any simpler, it would just mean that the software doesn't work any more. We are fortunate that you are not in charge of anything important at this stage of your own development.
-
I was erasing each word so I knew what I was done scanning.
My small system does all it does like a human brain (but not special system like this appears to be).
And so, what does it do?? Where does input go? Where is the rewards?
What can't it do?
Does it just hold info?
I noticed it works with events, time, language, physics, entities, etc.
-
And so, what does it do?? Where does input go? Where is the rewards?
What can't it do?
Does it just hold info?
Now that you're asking some smarter questions I'll make more of an effort to help you understand it. That diagram is just a map of a thing called a knowledge base. It shows the hierarchy of classes in the SUMO knowledge base. A class is a type of thing. You can have another class that is a more specialised type of the first thing. e.g. the class of animals and the class of cats which is a subclass of animals. All the subclasses of animals have in common the attributes of animals, but add some special features like whiskers or claws or flippers.
Just like maps of the world, you can have different kinds of maps that show different aspects of the same thing. For example what that map doesn't show is the containment hierarchy of the knowledge base. The containment hierarchy describes how things make up other things. For example, a normal cat would have four legs. Legs aren't a kind of cat so they're not a subclass of cat (but cat legs could be a subclass of animal legs) they are parts of a cat.
To see the entire knowledge base you would have to look at the source code. It's hundreds of thousands of lines of code written in a dialect of a language called KIF (Knowledge Interchange Format). The source code includes everything, but it can be easy to get lost in the details, that's why it's helpful to generate maps so we can find our way around more easily. The diagrams don't contain all the information that's needed for the software, they are just an aid to understanding.
Some kinds of maps have a start (inputs) and a finish (rewards) but not this one. This is like a map of the roads of a city which tells you where you can and can't go. This map tells you what can and can't be true. The knowledge base describes knowledge in such a way that you can use it to evaluate new knowledge.
If someone tells the AI something, the AI can translate what it has been told into KIF, and then see if it is in the knowledge base already. If it is in the knowledge base already then it "knows" it is true. If it isn't in the knowledge base, then the AI can check to see if it contradicts anything that is in the knowledge base already. If there is a contradiction then the AI "knows" that the new fact is false. Suppose that the new fact isn't in the knowledge base and it doesn't contradict anything that is already in the knowledge base? Then the new fact could be added to the knowledge base and that's how the AI learns.
There is no guess work or approximation or even magic involved. KIF and SUMO together allow you to perform calculations with knowledge in exactly the same way you would perform arithmetic with numbers.
-
Yes I have recently researched databases a bit.
The core of my AI system actually is a dynamic hierarchical system and so it would do the same thing as input comes in.
-
Yes I have recently researched databases a bit.
There's a substantial difference between databases and knowledge bases. This is a knowledge base. There is an even bigger gulf between "researching a bit" and spending decades working with the technology full-time, which is what I have done and continue to do (both databases and knowledge bases).
The core of my AI system actually is a dynamic hierarchical system and so it would do the same thing as input comes in.
But the question remains, just how would it do that? It won't happen by itself, and it won't happen by magic. Somebody has to program it and while you're waving your arms around and foolishly claiming to have invented it, somebody else already has.
-
Well the hierarchical system in mine is unique and only what we have exactly, soooo, nobody invented it yet. But I'd be glad if society did have it though.
-
Well the hierarchical system in mine is unique and only what we have exactly, soooo, nobody invented it yet.
Even if you had got out there and found and read and understood every published research paper you still wouldn't know that it's unique because not everything is published. Furthermore, until you have implemented it yourself and proven that it works, you can't even claim to have invented it yourself. This is just hubris on your part and I can tell you right now that it is getting in the way of anything that you might accomplish. Until you have the maturity and intelligence to sit down and research and build on the work of others, everything you do really will be a pointless waste of time. It won't even be fun for long, because pretty soon you'll realise that you're getting nowhere and it would be a real shame if you gave up at that point, like so many others in your position have done already.
-
Even if you had got out there and found and read and understood every published research paper you still wouldn't know that it's unique because not everything is published.
Furthermore, until you have implemented it yourself and proven that it works, you can't even claim to have invented it yourself. This is just hubris on your part and I can tell you right now that it is getting in the way of anything that you might accomplish.
Until you have the maturity and intelligence to sit down and research and build on the work of others, everything you do really will be a pointless waste of time. It won't even be fun for long, because pretty soon you'll realise that you're getting nowhere and it would be a real shame if you gave up at that point, like so many others in your position have done already.
intelligence to sit down and research
and
until you have implemented it
sums your post up
Do understand though that I am very intelligent, sit down lots, and research big time. And no matter what anyone says, I call myself a advanced researcher/neuroscientist/ulto-mega-knowledge-cloud-majiggy.
-
Even if you had got out there and found and read and understood every published research paper you still wouldn't know that it's unique because not everything is published.
Furthermore, until you have implemented it yourself and proven that it works, you can't even claim to have invented it yourself. This is just hubris on your part and I can tell you right now that it is getting in the way of anything that you might accomplish.
Until you have the maturity and intelligence to sit down and research and build on the work of others, everything you do really will be a pointless waste of time. It won't even be fun for long, because pretty soon you'll realise that you're getting nowhere and it would be a real shame if you gave up at that point, like so many others in your position have done already.
intelligence to sit down and research
and
until you have implemented it
sums your post up
Do understand though that I am very intelligent, sit down lots, and research big time. And no matter what anyone says, I call myself a advanced researcher/neuroscientist/ulto-mega-knowledge-cloud-majiggy.
I'm pretty much done with these...
(https://media.giphy.com/media/EP9aObQdHDABy/giphy.gif)
Locksuit, please stop that kind of behavior to make others feel discontent, which in turn sparks up derailed subjects that could give others trouble. You've been warned before.
We get it, you're the greatest.
I would advice everyone to never bother respond to anything that relates to his "Oh I'm the greatest" replies. It's just endless beating dead horses.
Ironically I have to make this post to give everyone a heads up.
Peace! O0
-
But I was only saying what I do man, don't get alarmed or hurt. The only thing I haven't done in that post above is the line saying "implement to prove".