Author Topic: How Can AI Be Used for Space Applications?  (Read 18734 times)

Offline Greg Hullender

  • Full Member
  • ****
  • Posts: 454
  • Seattle
    • Rocket Stack Rank
  • Liked: 332
  • Likes Given: 257
Re: How Can AI Be Used for Space Applications?
« Reply #60 on: 12/06/2022 03:36 pm »
The "current state of the art in AI" is to continue to throw more and more compute at the problem, using techniques (bog standard MLNNs) that were dismissed as dead ends decades ago, and to continue to improve in capability as a result of that increased available compute.
You left out "throw more data at the problem." :-) Lots of stuff that just doesn't work with small training sets does a decent job with hundreds (or thousands) of times the data. Assuming you have the compute power to handle it, of course.

Turing Machines (the majority of current computers) work by being very dumb very quickly, and its turned out that 'AI' can work very well by being very dumb in parallel, sufficient to be just as useful as out UTMs.
Of course, as has happened every single time an AI technique has been adopted into production, it will be dismissed in short order as "not real/true AI", as if the sole goal of AI is to replicate human-level intelligence and ignore the existence and utility of the huge range of other useful intelligences.
Yes, this attitude that "it's not AI if it actually works/is useful" is a big part of the reason why most serious researchers/engineers shun the "AI" label in favor of "machine learning (ML)." When you talk about ML, you make it clear that you're practical. If you talk about AI, you run the risk of people not taking you seriously.

A second factor, though, is that all existing useful implementations work by evading "the AI problem." Very often during design of a project I've had to tell management that we couldn't do something because "we'd have to be able to make the computer think." Over and over, we (and others) found solutions by coming up with clever ways to attack the problem without requiring any thinking on the part of the computer. When people learn what the solution actually was, they're invariably disappointed if they were hoping for "real AI" because it feels like we avoided the problem rather than solving it.

Online JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10739
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1216
  • Likes Given: 703
Re: How Can AI Be Used for Space Applications?
« Reply #61 on: 12/06/2022 03:48 pm »
"Trust me on this" -- While you may assert that we [or you?] know the full extent of human intelligence, and the computing power and complexity of the human brain, you and we do not. 
I'm simply saying that scaling up existing systems isn't going to produce human intelligence or anything like it, for the same reasons that scaling up a truck or a rocket isn't going to. ...

Well, you missed my point, but I see that I didn't convey my point as well as I should have.

Lack of computing power is not what stops current (or foreseeable) AI technology from having human-level intelligence.

"Lack of computing power" is one of the things stopping "forseeable" AI from having human level intelligence.

The AI algos suck because they are partly designed along political narrative lines; because they are poorly analogous to their human intelligence counterparts; because they don't use the same memory type that humans do; [perhaps Bohm's holographic model should be further studied]; AND... they lack the computing power of the human brain and mind.
Sometimes I just flat out don't get it.

Offline Greg Hullender

  • Full Member
  • ****
  • Posts: 454
  • Seattle
    • Rocket Stack Rank
  • Liked: 332
  • Likes Given: 257
Re: How Can AI Be Used for Space Applications?
« Reply #62 on: 12/06/2022 04:21 pm »
"Lack of computing power" is one of the things stopping "forseeable" AI from having human level intelligence.
I suppose it depends on your definition of "foreseeable." To me, that means anything based on technologies I've at least heard people propose--even if they aren't reduced to practice yet. But it doesn't include ridiculous things, like doing an atomic-level simulation of the human nervous system.

Something with real intelligence would have to be based on something different from anything I know of that anyone is working on today. That's all I mean by "foreseeable."

Offline edzieba

  • Virtual Realist
  • Senior Member
  • *****
  • Posts: 5082
  • United Kingdom
  • Liked: 7420
  • Likes Given: 36
Re: How Can AI Be Used for Space Applications?
« Reply #63 on: 12/06/2022 05:40 pm »
I'm loath to draw any distinction between 'real' intelligence and a tottering pile of hacks, since a) biological intelligence is a tottering pile of hacks that only mostly works (with legacy efficiency tricks like 'herd mentality' causing problems in modern systems, and the whole thing occasionally getting stuck in an infinite loop if the neurotransmitter balance is slightly off), and b) that gets into Cartesian Dualism (that there is some intangible quality that human minds posses and machines cannot).

Offline ppnl

  • Full Member
  • ***
  • Posts: 311
  • Liked: 196
  • Likes Given: 19
Re: How Can AI Be Used for Space Applications?
« Reply #64 on: 12/06/2022 09:41 pm »
I think there is some serious fuzziness in how people are thinking about this. Let me try to clarify.

First, universal Turing machines are just that. Universal. That means all computers are the same to within a polynomial time complexity. Neglecting memory size and processing speed any problem that one can solve any other can solve. They should also be able to simulate any object or process that exists in the universe. As long as the process isn't quantum in nature they should be able to simulate efficiently in the big O time complexity sense. That means we should be able to simulate brains. Short of trashing the Church/Turing thesis there is no way around this conclusion. People are free to reject the CT thesis but they should say so up front to avoid confusion.

So what do we need to simulate a brain? It is possible that we will need an increase in computing power of a hand full of orders of magnitude. That is challenging but is the easy part. After that all that is left is the software and algorithms. That may be the hard part.

Now, does anyone disagree with the truth and clarity of the above?


 

Online Robotbeat

  • Senior Member
  • *****
  • Posts: 36959
  • Minnesota
  • Liked: 21584
  • Likes Given: 11093
Re: How Can AI Be Used for Space Applications?
« Reply #65 on: 12/06/2022 09:59 pm »
But do you have an argument for such an opinion? A neuron is just a physical object that obeys physical laws. The Church-Turing thesis suggests that a computer program should be able to emulate the function of a neuron. While emulating a hundred billion neurons with a thousand trillion interconnections is challenging there is no new physics here as far as we can tell. Therefore it seems to be mostly an engineering problem.

...
I'm not arguing that intelligence is supernatural--just that we don't have the foggiest idea how to engineer such a thing. Nor is it reasonable to suppose that if we just make our computing systems bigger they'll somehow magically become intelligent.

I remember back in the late 80's a company I was working at, that had LOTS of Phd's, thought that neural networks would solve the A.I. hardware challenge. That was also about the time when "fuzzy logic" was thought to be the next revolution in consumer appliances, for making "smart washers" and such.

Needless to say the hype did not live up to reality, though no doubt we learned more about what we didn't know than what we did know.

Fast forward to fairly recently and we saw a similar boom and bust cycle with A.I. and its various subcategories. Though it looks like the bust cycle is not so bad with A.I., as we have found plenty of applications that can use its limited abilities.

But to your point, it does not yet appear that we understand how to make truly intelligent artificial intelligence, as opposed to smart tools.

So from that standpoint, of course "smart tools" like A.I. can be used for space applications. But I don't think they will be able to solve the challenges we have holding us back from expanding humanity out into space.
I would have agreed with both of you about a week or three ago. Now, I’m not so sure.

Things like GPT-3 seem remarkably flexible and powerful. It’s just a large language model with some significant limitations, but some of them seem to arise from technical constraints that could be overcome. Things like poor logic (ironic), the memory of a good fish (also ironic), etc.

Interact with chat.OpenAI.com for a few hours, see what others are doing, and then tell me how confident you are that a sufficiently large model, with tweaks in the next few years or decades, couldn’t approximate the kind of general intelligence that humans and animals exhibit.

I’m much less certain than I was just a month ago about us being unable to develop a general intelligence using sufficiently large neural net based models. Even more, before a year ago and the Dall-E 2 and stable diffusion stuff came out. They had this LLM take the SAT and it got over 1000. They had it take an IQ test and it scored 83.

Try it, don’t just read about it.
« Last Edit: 12/06/2022 10:01 pm by Robotbeat »
Chris  Whoever loves correction loves knowledge, but he who hates reproof is stupid.

To the maximum extent practicable, the Federal Government shall plan missions to accommodate the space transportation services capabilities of United States commercial providers. US law http://goo.gl/YZYNt0

Online DanClemmensen

  • Senior Member
  • *****
  • Posts: 3407
  • Earth (currently)
  • Liked: 2665
  • Likes Given: 1001
Re: How Can AI Be Used for Space Applications?
« Reply #66 on: 12/06/2022 10:00 pm »
I think there is some serious fuzziness in how people are thinking about this. Let me try to clarify.

First, universal Turing machines are just that. Universal. That means all computers are the same to within a polynomial time complexity. Neglecting memory size and processing speed any problem that one can solve any other can solve. They should also be able to simulate any object or process that exists in the universe. As long as the process isn't quantum in nature they should be able to simulate efficiently in the big O time complexity sense. That means we should be able to simulate brains. Short of trashing the Church/Turing thesis there is no way around this conclusion. People are free to reject the CT thesis but they should say so up front to avoid confusion.

So what do we need to simulate a brain? It is possible that we will need an increase in computing power of a hand full of orders of magnitude. That is challenging but is the easy part. After that all that is left is the software and algorithms. That may be the hard part.

Now, does anyone disagree with the truth and clarity of the above?

A Turing machine is a clocked digital system. Digital computers are a subset of all possible computers, so a UTM cannot simulate all possible computers. The two notable extensions are analog computers and non-clocked digital systems. Biological systems do not appear to be clocked, and they appear to incorporate analog components. It is not clear that a UTM can simulate a system with analog components in polynomial time.

I personally believe that "intelligence" will end up getting implemented in "traditional" computers (i.e., clocked digital logic). By "intelligence" I mean a system that passes an extended version of the Turing test. However, if this does not happen, you don't need to invoke quantum theory. You can add analog elements instead.

Online Robotbeat

  • Senior Member
  • *****
  • Posts: 36959
  • Minnesota
  • Liked: 21584
  • Likes Given: 11093
Re: How Can AI Be Used for Space Applications?
« Reply #67 on: 12/06/2022 10:05 pm »
Iím pretty sure ChatGPT could pass the Turing test if implemented and judged by most people. The most obviously machine aspect of ChatGPT is that the responses are much faster than a human.

ChatGPT simulates a dumb human (but really good at English class assignments) really well.
Chris  Whoever loves correction loves knowledge, but he who hates reproof is stupid.

To the maximum extent practicable, the Federal Government shall plan missions to accommodate the space transportation services capabilities of United States commercial providers. US law http://goo.gl/YZYNt0

Offline ppnl

  • Full Member
  • ***
  • Posts: 311
  • Liked: 196
  • Likes Given: 19
Re: How Can AI Be Used for Space Applications?
« Reply #68 on: 12/07/2022 12:27 am »
I think there is some serious fuzziness in how people are thinking about this. Let me try to clarify.

First, universal Turing machines are just that. Universal. That means all computers are the same to within a polynomial time complexity. Neglecting memory size and processing speed any problem that one can solve any other can solve. They should also be able to simulate any object or process that exists in the universe. As long as the process isn't quantum in nature they should be able to simulate efficiently in the big O time complexity sense. That means we should be able to simulate brains. Short of trashing the Church/Turing thesis there is no way around this conclusion. People are free to reject the CT thesis but they should say so up front to avoid confusion.

So what do we need to simulate a brain? It is possible that we will need an increase in computing power of a hand full of orders of magnitude. That is challenging but is the easy part. After that all that is left is the software and algorithms. That may be the hard part.

Now, does anyone disagree with the truth and clarity of the above?

A Turing machine is a clocked digital system. Digital computers are a subset of all possible computers, so a UTM cannot simulate all possible computers. The two notable extensions are analog computers and non-clocked digital systems. Biological systems do not appear to be clocked, and they appear to incorporate analog components. It is not clear that a UTM can simulate a system with analog components in polynomial time.

I personally believe that "intelligence" will end up getting implemented in "traditional" computers (i.e., clocked digital logic). By "intelligence" I mean a system that passes an extended version of the Turing test. However, if this does not happen, you don't need to invoke quantum theory. You can add analog elements instead.

Asynchronous digital systems have the same computational power as clocked digital systems. This becomes obvious when you consider that they both use the same universal logic gates and the same boolean algebra. Any asynchronous digital circuit can immediately be implemented as a clocked digital circuit or simply programmed as a computer program. Clock signals are really just a kludge to solve some engineering problems with asynchronous circuits. The problem is the data paths from input to output may be of very different lengths. This creates race conditions and for a large circuit the output may never be valid. A timing signal can latch the output to a valid state until the next state is valid.

A few decades ago they started experimenting with asynchronous sections in microprocessors to make them a little faster and use less energy. I think all modern processors have asynchronous sections. But it is just an engineering kludge that gets a little more performance.

The problem with analog computers is they really suck. There is no way to control the noise so the complexity of the calculations is severely limited. As a practical matter you will never calculate Pi to a thousand digits for example. And a digital computer can do anything that they can do faster and better. Floating point arithmetic is a thing on digital computers and they can have as many digits of accuracy as you want. I don't know if any analog computer is still in use anywhere in the world today. They are obsolete exactly because a digital computer can do everything that they can do.

Quantum computers arguably could offer an exponential speedup on certain limited types of computations. But it is hard to see how a warm wet brain could be a quantum computer.

I expect algorithmic progress decade on decade so that in 70 or so years we will look back on today the same way that we today look back on the invention of the transistor. Future computers used in AI may not look much like our computers but they will be universal Turing machines.     

Online Robotbeat

  • Senior Member
  • *****
  • Posts: 36959
  • Minnesota
  • Liked: 21584
  • Likes Given: 11093
Re: How Can AI Be Used for Space Applications?
« Reply #69 on: 12/07/2022 01:02 am »
I came across this interesting article about how AI is being used to conjure up completely new proteins very quickly.
https://www.nature.com/articles/d41586-022-02947-7


It occurred to me that this could enable all sorts of designer bugsorganisms for ISRU purposes, and maybe even terraforming.

Perhaps we could have bugsorganisms designed to survive the Martian day/night cycle, which would come alive during the day, to perform useful conversion of natural resources, like through Sabatier or whatever.

Could we even use AI to design complex ecosystems of organisms that would cope with the existing Mars conditions while working to transform the environment into one that's more human-friendly?
Yes, AI could potentially be used in a variety of ways for space applications, including for ISRU (in-situ resource utilization) and terraforming. For example, AI could be used to design and optimize proteins for specific conditions, such as the extreme temperatures and radiation levels on Mars. These proteins could be used in organisms that are capable of surviving and thriving on the Martian surface, and potentially even converting natural resources into usable materials.

In addition, AI could be used to design complex ecosystems of organisms that could adapt to the existing conditions on Mars and work to transform the environment over time. This could involve developing algorithms that can simulate and predict the behavior and interactions of different species, and optimize their performance in a given environment.

Overall, AI has the potential to greatly accelerate and improve our ability to utilize and explore space, by enabling us to design and optimize complex systems that can survive and thrive in challenging environments.
Quote
Tell me more, with specifics on the engineering involved.

In terms of specific engineering applications, AI could be used in a variety of ways to support space exploration and utilization. Some examples include:

* Designing and optimizing spacecraft systems and components: AI algorithms could be used to design and optimize spacecraft systems and components, such as propulsion systems, power systems, and communication systems, to improve performance and reduce costs. For example, AI could be used to model and simulate the behavior of different spacecraft components, and identify optimal configurations and designs that meet specified performance criteria.

* Planning and executing space missions: AI could be used to plan and execute space missions, by developing algorithms that can generate and evaluate potential mission plans, and identify optimal strategies for achieving mission objectives. This could involve simulating the behavior of spacecraft and other systems, and optimizing their performance to achieve desired outcomes.

* Analyzing data from space missions: AI could be used to analyze data from space missions, such as sensor data from spacecraft, to identify patterns and trends, and make predictions about future events. This could involve developing algorithms that can process and interpret large amounts of data, and extract useful insights and knowledge from it.

* Developing and deploying intelligent robots: AI could be used to develop and deploy intelligent robots that are capable of autonomously exploring and operating in space. This could involve developing algorithms that enable robots to perceive and interact with their environment, and make decisions based on that information. For example, AI could be used to enable robots to navigate and manipulate objects, and perform tasks such as collecting samples or repairing equipment.

Overall, AI has the potential to greatly enhance our ability to explore and utilize space, by enabling us to design and optimize complex systems, plan and execute missions, analyze data, and deploy intelligent robots.
« Last Edit: 12/07/2022 01:04 am by Robotbeat »
Chris  Whoever loves correction loves knowledge, but he who hates reproof is stupid.

To the maximum extent practicable, the Federal Government shall plan missions to accommodate the space transportation services capabilities of United States commercial providers. US law http://goo.gl/YZYNt0

Offline ppnl

  • Full Member
  • ***
  • Posts: 311
  • Liked: 196
  • Likes Given: 19
Re: How Can AI Be Used for Space Applications?
« Reply #70 on: 12/07/2022 02:12 am »
Iím pretty sure ChatGPT could pass the Turing test if implemented and judged by most people. The most obviously machine aspect of ChatGPT is that the responses are much faster than a human.

ChatGPT simulates a dumb human (but really good at English class assignments) really well.

The sad fact is that some really simple chat-bots has passed a Turing test from people who should know better. Here is my interaction:

ppnl: Hi!
AI: Hello! How can I help you today?
ppnl: What is 2+2?
AI: 2 + 2 = 4. Is there anything else you would like to know?

It correctly parsed the question and calculated the answer. It wouldn't be hard to write a program to do this. But a program that learned for itself how to do this is more impressive.

ppnl: Why did the chicken cross the road?
AI: There are many different jokes and puns that use this question as a setup, but the most common answer is "to get to the other side." This answer is a play on the idea that chickens are not particularly intelligent animals, so they would not have any complex motivation for crossing the road. Some other possible answers to this question include:

    To escape from a predator
    To reach a food source on the other side of the road
    To explore their surroundings
    To join other chickens on the other side of the road
    As a dare, or as a way to show off to other chickens

Ultimately, the answer to this question will depend on the context in which it is asked and the person who is answering it.

Ok, reasonably impressive. It covered the context as a joke and as a serious question. Not sure how it learned this from training text.

ppnl: How many chickens does it take to screw in a light bulb?
AI: I'm sorry, but I am not capable of performing physical tasks or manipulating objects. I am a large language model trained by OpenAI, so I can provide information and answer questions, but I cannot perform actions in the real world.

A clear miss. It missed the joke context. Worse it misunderstood that I was asking it to perform a physical task.

ppnl: How many light bulbs does it take to screw in a chicken?
AI: As I mentioned before, I am not capable of performing physical tasks or manipulating objects. I am a language model, so I can only provide information and answer questions based on the text that I have been trained on. It is not possible for me to screw in a chicken, or for any number of light bulbs to do so. Can I help you with anything else?

It is impressive that that it made the connection to the previous question. But it still seems to think I am asking it to do something. It does say light bulbs cannot screw in chickens.

ppnl: Can a person screw in a light bulb?
AI: Yes, a person is capable of screwing in a light bulb. In most cases, this involves using a screwdriver to            turn the base of the light bulb, which is threaded, in a clockwise direction until it is securely attached to the   light fixture. Some light fixtures may require a different tool or method for changing the light bulb, so it is important to refer to the instructions for the specific fixture being used.

Screwdriver? I can almost see how training on text might produce this strange answer. It clearly fails my Turing test but then many people I talk to online fail my Turing test so...

I remember when the Hubble space telescope was being built they were having trouble with the software that would prevent the telescope from inadvertently pointing at the sun or other bright objects. They were countless million over budget. Now I wonder if you could just simulate the situation and let it teach itself to keep safe. Would NASA trust such a program?



 

Online DanClemmensen

  • Senior Member
  • *****
  • Posts: 3407
  • Earth (currently)
  • Liked: 2665
  • Likes Given: 1001
Re: How Can AI Be Used for Space Applications?
« Reply #71 on: 12/07/2022 02:19 am »
I think there is some serious fuzziness in how people are thinking about this. Let me try to clarify.

First, universal Turing machines are just that. Universal. That means all computers are the same to within a polynomial time complexity. Neglecting memory size and processing speed any problem that one can solve any other can solve. They should also be able to simulate any object or process that exists in the universe. As long as the process isn't quantum in nature they should be able to simulate efficiently in the big O time complexity sense. That means we should be able to simulate brains. Short of trashing the Church/Turing thesis there is no way around this conclusion. People are free to reject the CT thesis but they should say so up front to avoid confusion.

So what do we need to simulate a brain? It is possible that we will need an increase in computing power of a hand full of orders of magnitude. That is challenging but is the easy part. After that all that is left is the software and algorithms. That may be the hard part.

Now, does anyone disagree with the truth and clarity of the above?

A Turing machine is a clocked digital system. Digital computers are a subset of all possible computers, so a UTM cannot simulate all possible computers. The two notable extensions are analog computers and non-clocked digital systems. Biological systems do not appear to be clocked, and they appear to incorporate analog components. It is not clear that a UTM can simulate a system with analog components in polynomial time.

I personally believe that "intelligence" will end up getting implemented in "traditional" computers (i.e., clocked digital logic). By "intelligence" I mean a system that passes an extended version of the Turing test. However, if this does not happen, you don't need to invoke quantum theory. You can add analog elements instead.

Asynchronous digital systems have the same computational power as clocked digital systems. This becomes obvious when you consider that they both use the same universal logic gates and the same boolean algebra. Any asynchronous digital circuit can immediately be implemented as a clocked digital circuit or simply programmed as a computer program. Clock signals are really just a kludge to solve some engineering problems with asynchronous circuits. The problem is the data paths from input to output may be of very different lengths. This creates race conditions and for a large circuit the output may never be valid. A timing signal can latch the output to a valid state until the next state is valid.

A few decades ago they started experimenting with asynchronous sections in microprocessors to make them a little faster and use less energy. I think all modern processors have asynchronous sections. But it is just an engineering kludge that gets a little more performance.

The problem with analog computers is they really suck. There is no way to control the noise so the complexity of the calculations is severely limited. As a practical matter you will never calculate Pi to a thousand digits for example. And a digital computer can do anything that they can do faster and better. Floating point arithmetic is a thing on digital computers and they can have as many digits of accuracy as you want. I don't know if any analog computer is still in use anywhere in the world today. They are obsolete exactly because a digital computer can do everything that they can do.

Quantum computers arguably could offer an exponential speedup on certain limited types of computations. But it is hard to see how a warm wet brain could be a quantum computer.

I expect algorithmic progress decade on decade so that in 70 or so years we will look back on today the same way that we today look back on the invention of the transistor. Future computers used in AI may not look much like our computers but they will be universal Turing machines.   
I was not attempting to claim that the alternatives (async digital and analog) are useful. I'm just pointing out that the flat assertion that a UTM can do any computing task is not strictly true in theory. Furthermore, biological intelligence appears to use both. Note that async digital is continuous in the time domain, so it is basically analog in the time domain.

Offline Greg Hullender

  • Full Member
  • ****
  • Posts: 454
  • Seattle
    • Rocket Stack Rank
  • Liked: 332
  • Likes Given: 257
Re: How Can AI Be Used for Space Applications?
« Reply #72 on: 12/07/2022 03:38 am »
So what do we need to simulate a brain? It is possible that we will need an increase in computing power of a hand full of orders of magnitude. That is challenging but is the easy part. 
If you're talking about simulating a brain on the atomic level, then you need a lot more than a "handful of orders of magnitude," unless your hands are unusually large. :-) It's not clear to me that we could set up such a simulation anyway--simulating single protein molecules is challenging at the moment.

If you're imagining that we understand the brain well enough to set up a simulation of it at something other than the atomic level, I think you're seriously misinformed.

Offline Greg Hullender

  • Full Member
  • ****
  • Posts: 454
  • Seattle
    • Rocket Stack Rank
  • Liked: 332
  • Likes Given: 257
Re: How Can AI Be Used for Space Applications?
« Reply #73 on: 12/07/2022 03:50 am »
Interact with chat.OpenAI.com for a few hours, see what others are doing, and then tell me how confident you are that a sufficiently large model, with tweaks in the next few years or decades, couldnít approximate the kind of general intelligence that humans and animals exhibit.
I played with it a bit just today, in fact. It's quite impressive for what it is, which is mostly a question-answering system.

There is a certain tendency to look at results that amaze us and disregard ones that are disappointing. For me, most of the responses were of the form "I can't help you with that." Some were very impressive indeed, but a couple were way off base. For example:

I tried making a statement instead of asking a question, "The sun is the nearest star to Earth," and it assured me that a) the sun is not a star and b) the sun is a star.

I asked it how to take a square root, and the answer was mostly nonsense with one useful fact--that Newton's method would do it. You'd still have to look that up on Wikipedia, but I can't claim the answer was 100% useless.

I think the best way to think of it is that it's a really clever database lookup tool. A system like this with a database of scientific/technical material might be very useful. But, no, it doesn't lead me to think it might develop intelligence just from more data or more processing power. It'll just give better answers to more questions and do it faster and for more people at the same time. There really is more to intelligence than that. :-)

For me, the most impressive thing is that it doesn't use a formal language model; it has developed a language model from large blocks of text without having any idea what a noun or a verb is. (Or so I'm led to believe; I haven't seen a formal description of the system yet.)

Offline ppnl

  • Full Member
  • ***
  • Posts: 311
  • Liked: 196
  • Likes Given: 19
Re: How Can AI Be Used for Space Applications?
« Reply #74 on: 12/07/2022 04:33 am »



I was not attempting to claim that the alternatives (async digital and analog) are useful. I'm just pointing out that the flat assertion that a UTM can do any computing task is not strictly true in theory. Furthermore, biological intelligence appears to use both. Note that async digital is continuous in the time domain, so it is basically analog in the time domain.

And I am flatly asserting that a UTM can do any computational task that is doable. It can simulate asynchronous or analog systems to any level of fidelity you want. It can almost always do it cheaper and easier than the analog or asynchronous system that it is replacing.
 

But unless you also claim that this is relevant to the power of AI then it might also be off topic.


Offline ppnl

  • Full Member
  • ***
  • Posts: 311
  • Liked: 196
  • Likes Given: 19
Re: How Can AI Be Used for Space Applications?
« Reply #75 on: 12/07/2022 04:51 am »
So what do we need to simulate a brain? It is possible that we will need an increase in computing power of a hand full of orders of magnitude. That is challenging but is the easy part. 
If you're talking about simulating a brain on the atomic level, then you need a lot more than a "handful of orders of magnitude," unless your hands are unusually large. :-) It's not clear to me that we could set up such a simulation anyway--simulating single protein molecules is challenging at the moment.

It is possible in a thought experiment but as a reality? No.

Quote
If you're imagining that we understand the brain well enough to set up a simulation of it at something other than the atomic level, I think you're seriously misinformed.

No we don't understand the brain well enough to simulate it at the atomic level or any other level. But there is no reason that we cannot come to understand it at a higher level than atoms. Neural nets in computers is a good start but far from the full story. For example we don't know how the brain does back-propagation. It is a mystery. It has a solution.

Online JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10739
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1216
  • Likes Given: 703
Re: How Can AI Be Used for Space Applications?
« Reply #76 on: 12/07/2022 09:37 am »
I'm loath to draw any distinction between 'real' intelligence and a tottering pile of hacks...

Before I ask for ranch dressing with my word salad, when I read this far, I thought of a colony of ants. Surely they exhibit "real" intelligence, despite not using fire, the wheel, the lever, XOR logic gates and such.

Time for coffee.
Sometimes I just flat out don't get it.

Online JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10739
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1216
  • Likes Given: 703
Re: How Can AI Be Used for Space Applications?
« Reply #77 on: 12/07/2022 09:45 am »
Now, does anyone disagree with the truth and clarity of the above?

While all that does sound truthy to me, it is not all "clear", since "simulating" a human brain, other than by trad genetic activities, is not "easy" by any stretch.  The computing power is inadequate, and the algos are faulty.

AI's applicability for space applications is, well, a no-brainer.  There are any number of specific applications that AI can profitably be applied.  Find a problem, and write the literature, errrr, software necessary to solve the problem.

Perhaps over time sentience will occur, but there are hard space problems needing solution right now.
Sometimes I just flat out don't get it.

Online JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10739
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1216
  • Likes Given: 703
Re: How Can AI Be Used for Space Applications?
« Reply #78 on: 12/07/2022 09:56 am »
But it is hard to see how a warm wet brain could be a quantum computer.

Allow me to help out by first pointing out that ALL wet brains that we know of exist in the quantum foam.  Consider also the fact that the neuron is very close to the scale of quantum events.  Several billion years of evolution within a quantum universe cannot be disposed of with a wave of the hand, simply because the connection is not well known. 

Remember how they used to talk about "junk" DNA?  I was always like, it's there for a reason; just because you don't know how it works is not excuse for calling it "junk".

Now, that we exist in a quantum universe doesn't solve the problem of simulating a sentient intelligence, but it does at least help you understand where the simulation needs to take place.
Sometimes I just flat out don't get it.

Online JohnFornaro

  • Not an expert
  • Senior Member
  • *****
  • Posts: 10739
  • Delta-t is an important metric.
  • Planet Eaarth
    • Design / Program Associates
  • Liked: 1216
  • Likes Given: 703
Re: How Can AI Be Used for Space Applications?
« Reply #79 on: 12/07/2022 09:59 am »
How many light bulbs does it take to screw in a chicken?

Bingo.
Sometimes I just flat out don't get it.

Tags:
 

Advertisement NovaTech
Advertisement SkyTale Software GmbH
Advertisement Northrop Grumman
Advertisement
Advertisement Brady Kenniston
Advertisement NextSpaceflight
Advertisement Nathan Barker Photography
1