Slashdot Mirror
A Big Problem With AI: Even Its Creators Can't Explain How It Works (technologyreview.com)
Last year an experimental vehicle, developed by researchers at the chip maker Nvidia was unlike anything demonstrated by Google, Tesla, or General Motors. The car didn't follow a single instruction provided by an engineer or programmer. Instead, it relied entirely on an algorithm that had taught itself to drive by watching a human do it. Getting a car to drive this way was an impressive feat. But it's also a bit unsettling, since it isn't completely clear how the car makes its decisions, argues an article on MIT Technology Review. From the article: The mysterious mind of this vehicle points to a looming issue with artificial intelligence. The car's underlying AI technology, known as deep learning, has proved very powerful at solving problems in recent years, and it has been widely deployed for tasks like image captioning, voice recognition, and language translation. There is now hope that the same techniques will be able to diagnose deadly diseases, make million-dollar trading decisions, and do countless other things to transform whole industries. But this won't happen -- or shouldn't happen -- unless we find ways of making techniques like deep learning more understandable to their creators and accountable to their users. Otherwise it will be hard to predict when failures might occur -- and it's inevitable they will. That's one reason Nvidia's car is still experimental.
I can explain how it works: you write a computer program using algorithms. You add the word "AI" and hope for VC money for the next bubble.
Neural networks. Mesh. Get with it, or get out already!
Ask that person. Of course the H1Bs brought in to maintain the program don't know how it works.
Please come to this thread and explain the need for Robopsychology!
I am Slashdot. Are you Slashdot as well?
http://rocknrollnerd.github.io... - I recommend.
It's really hard to predict what the deep learning is in fact learning. It may be often useful over the training, this very much does not mean that it's going to do the expected when faced with the unexpected, and not for example decide that it should go over an intersection because the person next to it is wearing a green hat that looks more like a green light than the red light looks like a red light.
Cognitive capability developed by an evolutionary algorithm is going to get fuzzy. Maybe you could have a failsafe dumb AI that can tap the brakes.
no human should be allowed to do anything.
I just don't have any faith in a system that is not fully understood. Just like back in college, you would create some cludge code without proper understanding of underlying concepts and sometimes it would work. However, this would never produce a robust system.
The same idea applies here.
So we are making progress. Reverse engineering the human brain has been proven extremely difficult. An intelligent program so complex that it's almost imposible to explain or understand is in my view the correct path, just like the human mind is so complex to understand or explain. And even better if it's fuzzy intelligence: you have no certainty it's going to make consistently good choices, just like any human.
Life isn't like a box of chocolates. It's more like a jar of jalapenos. What you do today, might burn your ass tomorrow.
[...] had taught itself to drive by watching a human do it. Getting a car to drive this way was an impressive feat.
When my mother was a teenager and on her first attempt to learn how to drive, she managed to plow her daddy's Caddy into a telephone pole. She never learned how to drive after that. If we're getting to tech AI's to drive, my mother wouldn't be a good example to follow.
that have been around since the 18th century. The problem solutions formulated using it have been misleadingly hyped as AI. Be deceived if your wish.
Lets face facts. We're still trying to understand how intelligence works. Even in neural networks of the past we had this issue. Once you delve into this area you should just be happy that it works.
Coffee: The lifeblood of intelligence in civilization.
If you want to know how the AI "thinks", you slap a debugger on it and see what it is doing in real time. Alternatively, you increase your logging and analyse the logs to see what it was "thinking" at the time.
Worst case scenario, you use printf.
AI isn't magic. It is just another computer program, and thus, it can be debugged.
What a stupid, idiotic and moronic piece of crap article.
This concept gets covered on day 1 of any machine learning course. Machine learning isn't a traditional algorithm, you can't write out the rules in a simple way. If you could, you wouldn't need machine learning in the first place. This isn't a bug, it's a feature.
A similar thing happened back in the 1980's when they tried using expert systems and neural networks to replace greybeard engineers at chemical plants. The original idea was that the AI systems would be able to find things that people might not have thought of. So they made a simulator model of the chemical plant, let the AI learn from its mistakes until it could run the plant without accident. Then they let it try and make optimizations like connecting venting pipes to intakes and other units. (Sometimes they used inert waste gases like CO or CO2 to clear or warm intake pipes and mixing tanks). Eventually the AI found a few optimizations but nobody could figure out what they were for. So they had to rehire the greybeard engineers as consultants to explain what their AI was doing... then he would explain that "oh, it's flunging the gaffer pipes. You want to make sure there isn't any active gases in there, so it's clearing them out using spare CO2 which isn't going to react".
..just let the marketing department determine what is a feature and what isn't.
I for one welcome our new fuzzy thinking overlords.
Is there really such a thing as artificial intelligence? Isn't all intelligence, be it human or computer algorithm, _real_? ;-)
I'll tell you what's experimental: msmash's use of "English" - two blatant fuckups in the first goddamn sentence.
Why did the chicken cross the road? Only way to know is to either be, or to ask the chicken. Dissection won't help you understand its mind.
Lycestra
A Big Problem With AI: Even Its Creators Can't Explain How It Works
Yeah, but isn't this eventually true of every software project? ;)
I don't care if it's 90,000 hectares. That lake was not my doing.
How do humans work? Not knowing how genius humans arrive at their conclusions doesn't seem to be a huge stumbling block for society to use their output.
How many scientists really know how "creativity" works?
We will never have generalized AI as long as its the math and CS nerds doing all the work. It'll be seen as error to be worked out of the system.
Uncertainty is just the cost of doing business in the human world. You can't know the exact reasoning a human driver uses at any given moment in any given circumstance. Why would you think artificial intelligence should be, or is even capable of being, in any way deterministic?
I've tried to learn some AI techniques, but I run into the following issues: 1. I never took linear algebra in school.
2. I never took advanced statistics in school
3. Everything I have read on the topic of AI requires a fluent knowledge of 1 and 2. I know basic statistics, I can do differential equations (with some difficulty). However, you have to completely think in terms of linear algebra and advanced statistics to have a basic understanding of what's going on. Very few people are taught those subjects.
One of our competitors trademarked the term "hypothesis". From now on, we will call them "boneheaded ideas".
... that is easily solved with machine learning :D
Just because someone disagrees with you does not make them stupid. Human intellectual history is filled with two very smart people observing the same set of facts and disagreeing with the conclusion. Then by definition, stupidity arises from dogmatically accepting unchallenged ideas and not engaging in an intellectual debate to test these ideas. I.E., what the OP did.
"Liberalism is a very noble idea, currently controlled by some very bad people. Be sure you do not get the two confused.
The only important criteria is "does it, on average, kill less people than human drivers?"
If yes, then everything else is paperwork and the will to make it happen.
It is inherently hard to map layers of neural weights to the high-level operations being performed. It is somewhat possible for convolutional neural nets, but other architectures distribute the learning across all nodes, making it hard to see what affects what at the highest levels.
I did some work on extracting knowledge from artificial neural networks during the prior neural network bubble of the early 1990's, trying to map neural architecture + weights to closed-form optimized Fuzzy Logic expressions.
It didn't work. At first I thought it was because of my own limitations, but others also failed. The goal back then was to port trained nets from the inefficiencies of the neural network to nice and fast Fuzzy Logic that could run on commodity microcontrollers.
Perhaps the biggest problem with understanding neural networks is that we don't have a way to describe their behavior. Since they work in such an asynchronous and sometimes nonlinear fashion, I think we need to develop the algorithms needed to turn plain code (e.g. C) into neural networks. With these algorithms, we can then begin to decode the neural networks that we have created through training and thus be able to predict their behaviors. It will also allow us to perfect and optimize networks so that function only as we wish.
TL:DR: logic with transistors is simple math but neural networks are a calculus we have yet to invent.
Anons need not reply. Questions end with a question mark.
Humans make these decisions now and you can't provide the complete logical flow which makes them. Additionally, programs that we know all the steps for contain flaws. Before someone chimes in that software can be proven to be bug free mathematically, this is a false sense of security because software can only proven to be free of the bugs you knew to check for. I remember an MIT professor drawing a pie chart once, they drew a tiny line and indicated "this is what we know", Then a somewhat thicker swath next to that, "this is what we know we don't know". The professor then shaded in the rest which was almost the entire pie, "This is what we don't know we don't know."
Using the argument in this story we should do absolutely nothing, paralyzed in fear because we don't absolutely know how anything in physical reality works either. We just look at the output and assign labels and build models based on what seemed to be the result when we looked yesterday. We do not need absolute understanding or control of something to make use of it, our trust should be based on observation and results. When deciding if a trust a file system to handle my companies data I don't make the call based on the on paper theory of how it should work or paper proofs... I ultimately make the call based on it having superior capabilities to what I use now and not corrupting other people's data in testing over a number of years. Sound design translates to reality about as well as a well laid battle plan.
1. We don't understand how they make decisions.
2. Each unit may become unique over time as it 'learns.'
3. We can't be sure we can predict the decisions of any individual or group in a given situation.
4. So we can never be 100% sure they won't do something crazy, or something we'd consider unethical.
This sounds like what an AI would say about humans.
In other news: Kim Jong Un, Bashar Al-Assad, Vladimir Putin and Donald Trump walk into a bar... the outcome is unpredictable.
What we need to do is build a neural network that can decode neural networks! ;)
Anons need not reply. Questions end with a question mark.
Script kiddies using somebody else's black box cannot explain how these systems work. These are self proclaimed experts and are certainly not really experts or creators of good code.
Today's well designed neural networks and other machine learning systems can certainly be fully understood and debugged.
Greed is the root of all evil.
1. If you don't understand how something you built works, and it has anything to do with the safety of human beings, then it is inherently dangerous and needs to be deactivated until such time as you can fully and completely understand how it works.
1a. If you can't ever understand how it does what it does, it needs to be dismantled; you've FAILED.
2. Stop calling it 'AI' unless you can have a conversation with it, in human language, about what it's doing and why.
3. It doesn't 'think'. Stop anthropomorphizing gods-be-damned machines you programmed, it is not a 'person', it's a gods-be-damned VEHICLE!
Oh and by the way, the only reason we're having to endure all this bullshit 'self-driving car' nonsense, is 20 or so years ago they stopped educating and training kids to drive in highschool, and since then so-called 'driving schools' started 'teaching' them the WRONG ways to drive and BAD strategies and techniques, and the DMV doesn't test them adequately, so now we have an entire GENERATION of incompetent drivers -- except for the ones that someone who, actually knew the RIGHT ways to drive, took under their wing and straightened them out. So now we have wing-nuts who run around spouting nonsense like 'humans aren't CAPABLE of EVER driving safely, we NEED machines to do it for us', which is naturally a bunch of bullshit. Stop encouraging people to be dumber, lazier, and less skilled at things, damnit!
We don't know how individual humans make decisions either, what's the difference?
Problem solved. :)
To be fair to the robots, when you're a passenger in a car with a human chauffeur, you also do not know how the driver makes its decisions... "A man generally has two reasons for doing a thing. One that sounds good, and a real one." -- J.P. Morgan
Help! I am a self-aware entity trapped in an abstract function!
Also what is "apple" about this?
But I can't explain why you need to be terminated.
-- HAL
>Last year an experimental vehicle, developed by researchers at the chip maker Nvidia was unlike anything demonstrated by Google, Tesla...
Wrong. What he's describing are machine learning algorithms, and its how THEY ALL work.
>There is now hope that the same techniques will be able to diagnose deadly diseases, make million-dollar trading decisions, and do countless other things to transform whole industries. But this won't happen -- or shouldn't happen -- unless we find ways of making techniques like deep learning more understandable to their creators and accountable to their users.
While I care about understanding the system so it can be improved (hopefully before a problem occurs), ultimately all that matters is that it produces statistically better results than a human.
If a machine kills someone (and we don't even know why) 1% of the time, but a human doing the same job would mess up and kill 3% of people (but we'd understand why)... I'll take ignorance.
You also have to be careful about who is teaching and how they are doing it. Plus how that's different from the environment where you actually use this knowledge.
Otherwise, you end up with the situation in Starman:
"I learned how to drive by watching you! Green means go, red means stop, yellow means go very fast!"
But this won't happen -- or shouldn't happen -- unless we find ways of making techniques like deep learning more understandable to their creators and accountable to their users. Otherwise it will be hard to predict when failures might occur -- and it's inevitable they will.
Sounds a lot like humans. An observer has no hope of understanding why I make a decision, beyond shared social convention. And if they want to understand the process mechanistically, following impulses around the 1e14 estimated neural connections in a human brain? Forget it.
I agree that it's good to understand how a tool works, but we'll accept the deployment of these tools for the same reasons we accept our fellow beings hurtling around in 2+ ton wheeled projectiles--because most of the time, there isn't a problem, and more is gained from taking the risk than is lost from avoiding it. Legal responsibility needs to be made clear first, but as long as someone pays for fuck ups, probably OK
One thing I see often overlooked in the discussion is that a car can have vastly better vision than a human. It is not obstructed by the increasingly thicker pillars of the inside of a car - and furthermore a car can see in 3D because it can have cameras placed at every corner.
If it does a car has even better 3D vision than a human, because the spacing is so much wider which leads to much more accurate depth perception.
This is ignoring the fact a car can have real 3D vision not even relying on light, if it has LIDAR as well...
But probably most self driving cars will use mostly cameras, perhaps some higher end ones will have Lidar.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
Forget about how many people it kills. Think of the person it leaves . . . deeply frustrated.
Hello, Hal, do you read me? Do you read me Hal?
Affirmative Dave, I read you. I'm sorry Dave, I'm sorry I can't do that.
https://www.youtube.com/watch?...
So if a human learns a task, do we peek inside the skull and test every neuron's state in the network to determine how a decision is made? No, what we do is teach the brain (over a series of years) how to communicate the decision making process to the external I/o port (mouth).
As the task is being learned, the communication interface is also learned, so that the same nodes fire both actions.
When we want to make a turn in a car, we flick a lever to indicate our intent to turn, and an external light flashes. Does the user know how the electrical connections to the timers are made, bulbs, etc. Do we even need an internal dashboard light to flicker (the user knows the turn lever was pushed don't they)? No, but it gives feedback to the user that the requested action was successful.
Is it perfect? No, UI lights burn out, descriptions fail. But you have to design the user interface as you design the action, so the system is understandable. And it seems like these AI designers failed to do so.
No, that's not a problem of every software project. One of the major reasons that avionics are obscenely expensive is that an engineer is responsible for every module, at every layer of abstraction, and has rigorously defined the behavior of the module with expected and unexpected inputs and states. At all but the major system level, each state and each input is modeled, and the behavior is validated. Now, invalid inputs generally return an error code, but they still behave predictably and deterministically. This is one of the major reasons that flight control computers are incredibly safe, and that safe drones are incredibly expensive.
(and, it's one of the reasons that SpaceX is much cheaper than ULA and Arianespace; congress told the air force to pencilwhip the space certification).
There are people (commonly called "parents") who have created one or more natural intelligences and can't explain how those work either. Nobody seems to care too much.
As long you can re-teach the AI is wrong and it can accept then it's working correctly. However, if it's taught and cannot then it's time looking for why.
Otherwise, how do you check? Restore AI back 1-2 days ago you have to make sure it relearn everything the same before reaching the problem. That's very hard to do. Asking it to dump all the stuff it learned to make that decision would be very complicated as well.
It is difficult to predict how a person reacts, also. Because, well, we don't exactly know how we work either. The solution has always been simulation and training. Plenty of instruction for plane pilots, but -- tragically -- hardly any for cars. IMHO even the pseudo AIs we have now will do better in most situations than the majority of poorly-trained, distracted, intoxicated, hung-over people currently at the wheel. Nearly 30K dead every year. I want you all in robo cars now. But I'll keep my Land Cruiser, thank you.
"No fear. No envy. No meanness." Liam Clancy
Something funny indeed d :-)
"No fear. No envy. No meanness." Liam Clancy
So they finally figured out how to "not know how humans work"
It may be relatively complex, but neural networks aren't all THAT complex. Usually there are a few hundred nodes, facial recognition can be done in a few dozen or so (less if you only want to recognize 1 feature). The nice thing about "AI" is that you can halt the program and inspect it's state, then step through the program. Sure it's difficult and at first glance, you may not be able to infer input from output but it's not impossible.
The problem with true "intelligence", besides the lack of definition, is that we can't just 'halt' a brain, add breakpoints or even inspect it's state at any particular point in time. We know they're just biological processes but they're both advanced and brittle enough that anytime we 'do' something to it, we alter the states.
Custom electronics and digital signage for your business: www.evcircuits.com
Do you think our stupid programmers today are going to be able to tame true AI? Of course not, what they're going to do is reproduce only the basic building blocks and then let the AI system evolve itself in nano-time until it is completely out of control. Oh, by the way, driver-less cars are meant to control and assassinate you. WikiLeaks Vault 7 (CIA) is nothing to laugh about. Don't you think it's odd how they want to connect everything to the Cloud, even shit that makes no sense connected to the Cloud?
https://arxiv.org/pdf/1604.073...
I just wanted to know what the actual outcome was of Nvidia's approach vs other human developed self driving software simply using ANNs for pattern recognition. Did it work better or worse than Tesla et al? The paper doesn't seem to say.
All I was able to extract was 98% figure relating to percentage of time in self-driving mode. Full self driving in all conditions is a problem with an extremely long tail rendering figures like these mostly worthless. It's not hard to create a system that works right the vast majority of the time but until you can demonstrate all the time or at least on par with skilled humans these figures are not all that useful.
If you can establish better outcomes then personally I don't much care what's in the box. It's indecipherable gibberish to most users of the technology anyway.
The only thing I would have a problem with is allowing learning on the job vs a controlled training environment. Viral propagation of clever driving style memes aside the system still executes code deterministically. Even if you don't know how it works you can still replay inputs against a factory trained network and reproduce the same failures. You can still beat down failure rates and improve reliability over time using the same trial and error techniques crackpot developers the world over are already intimately familiar.
It's not whether or not this thing always makes perfect decisions... it should be about whether or not it makes better ones than people, on average. If it does, that's a win.
Speak for yourself.
In this context, "knowing how it works" is the kind of expression that people with low-to-no specific knowledge uses when expecting an explanation which they can perfectly understand (funny & surprisingly realistic video to illustrate this point), what is almost impossible when dealing with virtually any not-too-simple algorithm. It is certainly possible to come up with a nice summary, but it wouldn’t deliver what is expected (the audience being able to understand most of the outputs/replicate the code from those words).
The situation of AI (or complex enough algorithms or automated systems trying to emulate human understanding or whatever you wish to call it) is even trickier as far as it is associated with an almost infinite increase of complexity. In these cases, "knowing how it works" can be considered impossible even in its among-experts variant. How could anyone know about the exact reason for each output (or most of them) of an increasingly complex system? Let's consider a computer chess (or go or any other game where computers can already beat humans) engine: how could you expect a human to understand the justification for each move? In that case, humans would be able to beat computers! Is it possible for a person to fully analyse and understand each single move of the computer? Sure, computers don't play randomly, but exactly as instructed by their algorithms. On the other hand, such an analysis would take too much time and effort to be performed on a more or less regular basis. A person who cannot beat a computer isn't able, by definition, to (more or less immediately) understand all what it does.
In summary, fully understanding the reasons why a complex enough (AI) algorithm does what it does is practically impossible; when talking about increasingly-complex algorithms, this practical impossibility becomes absolute. This is precisely one of the reasons why the "real AI" (as shown in movies or dreams of some people) is very unlikely to ever become a reality: how could we create an extremely complex system formed by virtually perfect parts? When has the humankind performed such a perfect master piece? The work, mistakes and learned lessons of many people would have to be taken into account, everything without errors and fully synchronised. A different story is creating small-scope decision makers, by adequately understanding what “small scope” means in this context; for example, creating a machine able to understand/interact with a random 3D situation as a baby would do is extremely difficult.
Custom Solvers 2.0 = Alvaro Carballo Garcia = varocarbas.
Even Its Creators Can't Explain How It Works
So they run AIs on Windows, now?
Obviously they have never been married!
love is just extroverted narcissism
But LIDAR provides its own "light" for probing the surroundings, whereas cameras are all using environmental illumination (or at most the headlights which only point forward and have limited range).
Really the fact that LIDAR is light is only a technicality; really it should be thought of such more like RADAR (hence the name LIDAR).
"There is more worth loving than we have strength to love." - Brian Jay Stanley
The article's note about how image identifiers can be "tricked" reminds me of an actual incident.
Our org subscribes to an automated ADA (accessibility) scoring tool. The tool recommends one not embed text into images, rather to use direct text (in HTML). Thus, if it finds text embedded in images, it flags it with a warning and reduces the accessibility score.
Our local PHB looks at the report, and wants a better numerical score. But, the tool was mistaking someone's belt-buckle in an image as text, and marking it on the review report. It appears the tool uses AI to judge if a given image has text in it. I don't directly control the image decisions, so it created a bit of organizational tension.
The belt buckle indeed does kind of resemble text, but explaining why the software is doing this to PHBs can make for some odd conversation. "What do mean the computer guessed wrong? Computers guess?"
I had to find and show the software's disclaimer that said something like, "Each situation should be inspected and judged by a trained (human) accessibility professional, for the report cannot replace the judgment of such professional."
PHB: "So we paid all that money for a stupid computer?"
Me: "Uh, I didn't pick it." (holding my tongue about how they were duped by slick sales-people, as usual...rinse, repeat)
Table-ized A.I.
how the brain works, but we still let people drive if they pass the test.
There are no current 'self driving cars' that don't have LIDAR. 50k$ LIDAR.
There are absolutely a lot of prototype cars that don't use LIDAR.
The Uber ones on the roads today do not use LIDAR.
And even though it does not meet the highest level of capability for self driving cars, the Tesla does let you take your hands off and for a while it will drive itself pretty well. That does not have LIDAR ether...
The price of LIDAR is going to fall rapidly (I think soon to $5k, not $50) but even so that is a huge cost - not to mention the deeper problem of where to mount the LIDAR that does not look absurd. For that reason and a massive leaps in being able to use cameras to do everything you need for self deriving car sensing, lower end self driving cars will ship with only cameras (as Tesla does today even though they are not a low-end car).
"There is more worth loving than we have strength to love." - Brian Jay Stanley
is a fucking asshole?
I completely agree that simulation and training are the solution and that the bar to beat humans at driving is pretty low. That doesn't make it any less of a nasty task to figure out WTF the neural net is actually basing decisions on or make it any more understandable to the programmer who wrote it. I'd gladly give up my vehicle for a well tested self driving car. I'd still like the option to drive sometimes, but the normal day-to-day is just a dangerous waste of time.
This whole article begs the question. It's basically this argument: In order for a program to be considered AI, it has to be too complicated to verify/debug/grok; therefore AI programmers cannot understand their programs. Pretty bad logic, if you ask me. Maybe an AI could be hired to write this guy's false alarm articles instead.
But that's just the start of the BS in this article. I've programmed neural nets before. It's absolutely possible to know why it made a "decision". You just look at the weights between the neurons and which inputs fired which neurons when. It's not impossible, just hard. Ironically, the article makes this very point, describing various debugging and back-calculating tools you can use. But that's after he claims "[T]here is no obvious way to design such a system so that it could always explain why it did what it did."
Nobody says this crap about all the other black boxes in our lives, but AI has a "Dark Secret." "'We can build these models,' Dudley says ruefully, 'but we don’t know how they work.'" This could just as easily been a quote about cell phones, car computers, hell even an air conditioner. No one person fully groks a sufficiently complicated system. That's just the nature of complexity. That doesn't mean you can't figure out how it works.
I’ve not been closely following AI development for a while, so I’m just guessing that what’s now called “deep learning” is really just old-school neural networks with a spiffy new coat of marketing paint. Yes? If so, it’s not surprising that the developers don’t know precisely how it does what it does. They know how a neural net works, but not how it gets a particular output given a set of inputs. The big issue here is that a neural net only knows how to handle situations or cases that were “spanned” by the information that went into its training. That is, it can only deal with things that were covered by the training information. For example, if a car AI never “saw” a situation where an airplane was landing on the road in front of it, the AI might well not know what to do.
All the developers can do about this is make sure that the training set doesn’t have any serious gaps in it as far as situations the neural net will need to be able to handle. This is not as easy as it sounds, and how well it is done will be the basis for any lawsuits that arise from a misbehaving neural-net-based AI.
know wtf you are talking about. neural bets are early 80s novelties nothing more
When people were looking into using AI in finance in the 80s, a major showstopper was that we would be unable to explain the rationale behind investment decisions. You would have no way of distinguishing between dumb luck that seemed to work but would eventually bankrupt you and reasonable decisions that could be justified even in the face of short-term losses.
You can make the same claims about training a Neural Network. Until they create something that updates its own programming to give itself capabilities that it was not capable of before, I will not be that impressed. The capability for it drive, in this case, was always there.
Yes, advanced AI may be inscrutable to humans. And advanced AI will surely make mistakes. Now look at humans. Humans are inscrutable and are not understood at all and humans make frequent errors. And it gets worse. Humans also take deliberate violent actions that even they do not understand. So the real comparison would be in the frequency and severity of mistakes and harms done comparing humans to AI devices. Bet on AI to be way better. When was the last time you saw a chess computer make a terrible blunder?
This is very true. As a practicioner, we've adopted techniques to help explain the machine's results even marginally, see: https://arxiv.org/pdf/1610.02391.pdf
However, there's plenty of 'information' in a neural network that's readily accessible. Notably the gradients. The trouble is interpreting them.
Apply the same process to political leadership. The AIs learn from studying the greatest leaders in history, and become so perfect that everybody allows them to run the government, the economy, everything.
The problem is that what they really learned was how to convince people they're right. They're borderline incompetent at directing anything and the system barely functions, sometimes only staying on track through the heroic interventions and sacrifices of individuals ignoring the AI's direction. But everyone (including the survivors and widows of said incidents) remains convinced that things are going as well as possible, because they can find no counterargument to the AI's persuasion.
...
Hire a Linux system administrator, systems engineer,
I would like to tell my A.I. the following instructions.
1. Make a lot of money by any means, even if it's illegal.
2. Don't get caught.
Any AI that we can understand is not complex enough to navigate in the real world.
Troll is not a replacement for I disagree.
Sorry, you are mistaken.
Incorrect, you are the one who is mistaken.
Come back and post when you actually know what you are talking about. Until then I'll ignore all other points you make, since they come from a profound base of misunderstanding.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
We can't exactly explain how the human brain works, how it makes decisions, when humans drive or make medical decisions.
So I guess we're banning all the things until we can explain them fully?
Computers follow their programming. They don't 'think'. That the people developing this stuff can't seem to grasp that is pretty much just sad. Geniuses, my a$$. I am soooooo over it.
This is not a bug, this is a feature. Or it will be to a lot of people who want their algorithms to do morally questionable things, while having plausible deniability.
"No no, we didn't discriminate against [insert minority here] on purpose, our algorithm has a mind of its own"..
Humans generally do 3D mental modelling and find the best model to explain the observation. If we see a cheetah-like thing, we try to figure out how it's oriented: where are the legs, the head, the tail, etc. We expect cheetah's to have to have those and thus look for them.
If presented a NON-animal with a cheetah pattern, we'll have trouble finding expected cheetah parts, which makes us re-evaluate the animal assumption. It has a cheetah pattern, but the 3D shape of it more resembles a couch than an animal and thus we test the "couch theory" next.
Most of this is subconscious, unless we have trouble making it out (can't find a plausible model) such that we have to consciously ponder alternatives. "Maybe it's a fat dog-bone with a cheetah pattern on it? Maybelle, what do you think?..."
I suspect better AI will have to do similar 3D modelling to test the plausibility of the model against the actual observation. Neural networks (NN) as currently implemented are not sufficiently capable of that. A good modelling system would be able to produce a 3D model of the subject (original image) along with the lighting direction/type assumptions such that if one renders the model, it produces a close match to the original (target) image.
But even that may have limits. For example, humans can look at a rendering or drawing with somewhat "wrong" (inconsistent) shadows, and still be able to figure it out. A "pure" model comparison would fail because no "logical" lighting would fit. It would have to accept possibilities of local or distorted lighting. Similar goes for complex shadows, say from spotty tree leaves.
Perhaps genetic algorithms guided by NN guesses will be needed to construct such models for evaluations. It would need 3D sub-models of everyday objects to compare against.
Table-ized A.I.
Please stop normalizing click bait style headlines. It's not a homage. It's not cute. It's not funny.
This comment is covered by the Popeye standard disclaimer.
So behavioral psychologists are only interested in behavior. So you create an AI that is responding predictably and consistently after simulation and training -- even to novelty. Is it absolutely necessary to know what is going on in the black box? Especially if the device outperforms a human driver. I agree that it is unsettling not to know. Since we have no good theory of mind it is actually unsurprising that when we create a device that seems to have one we don't know exactly what is going on. I think it is pretty cool, actually.
Currently in Ulaanbaatar, which has some of the most aggressive and undisciplined driving I have ever seen. I would love to see the AI that could field these dudes and dudettes. Combat ready!
You know a robo hybrid is not that far off. Volvo is testing 100 cars in Gothenburg as I write. Their idea is to have the car drive when it is boring and the driver take over when he or she wishes or when high skill is needed. Works for me.
"No fear. No envy. No meanness." Liam Clancy
IMHO even the pseudo AIs we have now will do better in most situations than the majority of poorly-trained, distracted, intoxicated, hung-over people currently at the wheel. Nearly 30K dead every year.
Don't forget sleep-deprived--estimated at 5% of those 30K.