Yoshua Bengio
speaker
2,216 appearances
5 recordings
5 series
first heard Oct 2018
last heard 7 May
Yoshua Bengio’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 — 3 in all, peaking in May 2026 with 1.
Appearances
They're not communication acts.
And the causal connection is happening at that level.
Like all scientific theories are about actual properties of the world and how they're causally related to each other.
And there's a reason for that.
Mathematically, when you express your explanation for the world in the language of what's actually going on in the world, rather than what people think or what people say, rather, you get better predictions.
No, but it's not enough to represent truth internally.
It needs to learn a language that we can query about what it thinks.
So the main reason why we need these verified truths isn't because of whether they're true or not.
In a sense, who cares about some theory, some theorem is true or not when you're talking about human psychology, right?
Why would it matter?
The only thing that matters is to teach the AI the syntax
of how to express actual properties of the world by opposition to the syntax of to express somebody said something, right?
And the reason we want to teach that syntax is that we can then later query using the same syntax, but on a different kind of statement, which are the statements about people and politics or whatever.
Yes, and it will use the coherence of different hypotheses about actual truth.
you know, how coherent is a particular hypothesis with all the other hypotheses that the system has about the world, right?
Just like a scientist would.
Like if somebody comes up with an explanation for something, and that explanation is not coherent with other things we believe strongly because of other evidence, then we're going to reject that explanation.
And the same thing is going to happen.
So it's going to be trained, in its training procedure, it is not just trained to predict the next thing,
That would be just autoregressive predicting of what's in the data.
Showing 661–680 of 2,216 · page 34 of 111
← Previous
Next →