Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017” • Hacker News Board

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#171

Post by georgespencer » Mon, Nov 14, 2016, 4:09 PM UTC

argonaut wrote: post #169

georgespencer wrote: post #160

Earlier quoted context omitted.

It doesn't seem like zero-shot classification to me. It still seems like image classification. You said: > What if every time Ford/GM/Toyota substantially changes the look of their cars, your classifier no longer recognizes them My answer was probably incomplete, but I took the above to mean that cosmetic changes to vehicles mean that classifiers no longer identify them as cars, and this detrimentally modifies the be…

"it moves at the speed a car moves at, it's in the road, it's overtaking on the right hand lane" is video classification, which is not solved. In fact, at least how you described it (you could probably change the problem statement to avoid this), this would involve an ML model that must learn a model of physics - also unsolved. You've just specified a manually hardcoded set of decision rules. This is not machine lear…

I think we're talking across one another.

I had thought that in your original post you were agnostic about the methodology for identifying a car, but were remarking that, in a world where it's possible to do it using whatever form of classification, it would be possible to 'stump' any reliable model by modifying the appearance of a car. I'm observing that any model for classification almost certainly would not rely on aesthetics.

> You've just specified a manually hardcoded set of decision rules. This is not machine learning, and is incredibly brittle.

I'm pointing this out to illustrate that the technology already deployed to solve this problem does not get confused by aesthetics.

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#172

Post by argonaut » Tue, Nov 15, 2016, 9:55 AM UTC

georgespencer wrote: post #171

argonaut wrote: post #169

Earlier quoted context omitted.

"it moves at the speed a car moves at, it's in the road, it's overtaking on the right hand lane" is video classification, which is not solved. In fact, at least how you described it (you could probably change the problem statement to avoid this), this would involve an ML model that must learn a model of physics - also unsolved. You've just specified a manually hardcoded set of decision rules. This is not machine lear…

I think we're talking across one another. I had thought that in your original post you were agnostic about the methodology for identifying a car, but were remarking that, in a world where it's possible to do it using whatever form of classification, it would be possible to 'stump' any reliable model by modifying the appearance of a car. I'm observing that any model for classification almost certainly would not rely o…

I was talking about deep learning. The comment I was replying to was making the specific problem seem as if it were easy. Certainly there may one day be a classification technique that does what you say will do. But you may as well have said there will one day be a perfect classification technique that will just perfectly output steering angles, end thread. What use is there in conjecturing about perfect unknown classification techniques? Not to mention that there is no guarantee such a perfect method would not rely on aesthetics. Even if the train set has more than just aesthetics (e.g. video of cars in motion) maybe this perfect classifier would just cheat and rely on aesthetics, you don't know.

So I'm pointing out the methodology you suggested is not currently feasible, or is currently widely considered by the community to be the wrong practical approach. Because theoretical solutions will not solve self driving cars.

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#173

Post by vidarh » Tue, Nov 15, 2016, 12:24 PM UTC

argonaut wrote: post #170

vidarh wrote: post #161

Earlier quoted context omitted.

No, you don't. You need to process enough of it to see how the majority of human drivers act in situations where the automated system currently would react substantially differently.

You've just described end-to-end-learning (e.g. the data is raw video/camera/radar/sensor data, the labels are steering angles, etc.) No autonomous vehicle manufacturer uses end-to-end learning. The only one to claim to use it was Comma.ai, and we all know how that went. All the autonomous car companies will manually label the camera images - e.g. given an image, draw boxes around where all the cars are.

Learning how to label camera images and how to respond to already detected features are separate issues. You can make the choice of whether to apply unsupervised training to either one separately.

This [1] blog post from Tesla explicitly claim that they are using unsupervised learning as one of their strategies to determine appropriate system response to specific detected objects in specific locations:

> This is where fleet learning comes in handy. Initially, the vehicle fleet will take no action except to note the position of road signs, bridges and other stationary objects, mapping the world according to radar. The car computer will then silently compare when it would have braked to the driver action and upload that to the Tesla database. If several cars drive safely past a given radar object, whether Autopilot is turned on or off, then that object is added to the geocoded whitelist.

> When the data shows that false braking events would be rare, the car will begin mild braking using radar, even if the camera doesn't notice the object ahead. As the system confidence level rises, the braking force will gradually increase to full strength when it is approximately 99.99% certain of a collision. This may not always prevent a collision entirely, but the impact speed will be dramatically reduced to the point where there are unlikely to be serious injuries to the vehicle occupants.

[1] https://www.tesla.com/blog/upgrading-autopilot-seeing-world-...

Re: Nvidia on new self-driving system: “basically 5 years ahead and coming in 2017”

#174

Post by tim333 » Tue, Nov 15, 2016, 1:36 PM UTC

emcq wrote: post #164

tim333 wrote: post #97

The PX 2 is kind of a cool computer. 8 teraflops, 250W, liquid cooled. I imagine it would run a good bit less than that most of the time. 8 teraflops is about 8% of Moravecs estimate of brain equivalence so assuming you use ~8% of your brain driving it may be about right.

The brain doesn't do floating point operations. You're trying to compare apples to oranges.

Yeah but Moravec's arguments were based on the rough processing power he found necessary to achieve equivalent performance in the simple robots he was building. So it's a two apples equals one orange for making fruit salad kind of estimate.