Yann LeCun
speaker
384 appearances
5 recordings
4 series
first heard Mar 2024
last heard 20 Jun
Yann LeCun’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 4 in all, peaking in Jan 2026 with 2.
Appearances
So we've been doing this with Ojepa architectures, basically. The joint embedding. Ojepa. So there, the compatibility between two things is, here's an image or a video, here's a corrupted, shifted, or transformed version of that image or video, or masked. And then the energy of the system is the prediction error of the representation
the predicted representation of the good thing versus the actual representation of the good thing. So you run the corrupted image to the system, predict the representation of the good input, uncorrupted, and then compute the prediction error. That's the energy of the system. So this system will tell you this is a good representation
If this is a good image and this is a corrupted version, it will give you zero energy if those two things are effectively, one of them is a corrupted version of the other. It gives you a high energy if the two images are completely different.
And we know it does because then we use those representations as input to a classification system.
I don't hate reinforcement learning, and I think it should not be abandoned completely, but I think its use should be minimized because it's incredibly inefficient in terms of samples. And so the proper way to train a system is to first have it learn good representations of the world and world models from mostly observation, maybe a little bit of interactions.
Yeah, now there's two things you can use. If you've learned a world model, you can use the world model to plan a sequence of actions to arrive at a particular objective. You don't need RL unless the way you measure whether you succeed might be inexact. Your idea of, you know, whether you were going to fall from your bike.
might be wrong, or whether the person you're fighting with MMA was going to do something and then do something else. So there's two ways you can be wrong. Either your objective function does not reflect the actual objective function you want to optimize, or your world model is inaccurate. So the prediction you were making about what was going to happen in the world is inaccurate.
So if you want to adjust your world model while you are operating in the world or your objective function, that is basically in the realm of RL. This is what RL deals with to some extent, right? So adjust your world model. And the way to adjust your world model, even in advance, is to explore parts of the space where you know that your world model is inaccurate.
That's called curiosity, basically, or play, right? When you play, you kind of explore part of the state space that you don't want to do for real because it might be dangerous, but you can adjust your world model without killing yourself, basically. So that's what you want to use RL for. When it comes time to learning a particular task,
You already have all the good representations, you already have your world model, but you need to adjust it for the situation at hand. That's when you use RL.
What's had the transformational effect is human feedback. There's many ways to use it, and some of it is just purely supervised, actually. It's not really reinforced by learning.
It's the HF. And then there is various ways to use human feedback, right? So you can ask humans to rate answers, multiple answers that are produced by a world model. And then what you do is you train an objective function to predict that rating. And then you can use that objective function to predict whether an answer is good.
And you can backpropagate gradient through this to fine-tune your system so that it only produces highly rated answers. That's one way. In RL, that means training what's called a reward model. Basically, a small neural net that estimates to what extent an answer is good.
It's very similar to the objective I was talking about earlier for planning, except now it's not used for planning, it's used for fine-tuning your system. I think it would be much more efficient to use it for planning, but currently it's used to fine-tune the parameters of the system. Now, there are several ways to do this. Some of them are supervised.
You just ask a human person, what is a good answer for this? Then you just type the answer. I mean, there's lots of ways that those systems are being adjusted.
I actually made that comment on just about every social network I can, and I've made that point multiple times in various forums. Here's my point of view on this. People can complain that AI systems are biased, and they generally are biased by the distribution of the training data that they've been using.
trend on, that reflects biases in society and that is potentially offensive to some people or potentially not. And some techniques to de-bias then become offensive to some people because of historical incorrectness and things like that. And so you can ask the question, you can ask two questions. The first question is, is it possible to produce an AI system that is not biased?
And the answer is absolutely not. And it's not because of technological challenges, although there are technological challenges to that. It's because Bias is in the eye of the beholder. Different people may have different ideas about what constitutes bias for a lot of things.
I mean, there are facts that are indisputable, but there are a lot of opinions or things that can be expressed in different ways. And so you cannot have an unbiased system. That's just an impossibility. And so what's the... What's the answer to this? And the answer is the same answer that we found in liberal democracy about the press. The press needs to be free and diverse.
We have free speech for a good reason. is because we don't want all of our information to come from a unique source. Because that's opposite to the whole idea of democracy and progress of ideas and even science, right? In science, people have to argue for different opinions and And science makes progress when people disagree and they come up with an answer and, you know, a consensus forms, right?
Showing 221–240 of 384 · page 12 of 20
← Previous
Next →