Very interesting set of slides
It seems the current state of prediction is only slightly better than the state of image recognition pre multiple level NNs
There might be still a theoretical jump that's needed
Predictive Learning [pdf]
11–20 of 41 posts
Re: Predictive Learning [pdf]
#12If page 33 depicts the working of the brain on a very high level, the world model (or simulator) residing inside the agent must contain a model/simulator of the agent itself. Could this give rise to self perception or consiousness?
this is an excellent point. This model has to be recursive and may be depth of recursion has something to do with self-perception?
Re: Predictive Learning [pdf]
#13If page 33 depicts the working of the brain on a very high level, the world model (or simulator) residing inside the agent must contain a model/simulator of the agent itself. Could this give rise to self perception or consiousness?
The idea that self-representations give rise to consciousness exists in neurophilosopy and it is closely related to the representational theory of consciousness and the higher-order monitoring theory:
https://plato.stanford.edu/entries/consciousness-representat...
https://plato.stanford.edu/entries/consciousness-higher/
https://mitpress.mit.edu/books/self-representational-approac...
http://www.nyu.edu/gsas/dept/philo/courses/consciousness05/L...
Re: Predictive Learning [pdf]
#14If page 33 depicts the working of the brain on a very high level, the world model (or simulator) residing inside the agent must contain a model/simulator of the agent itself. Could this give rise to self perception or consiousness?
During the speech [1], Yann (surprisingly) didn't mention consciousness at all. The focus of this segment was the need to "imagine" the future. The premise is that "common sense" – Yann's big theme of the talk – is about "filling in the gaps" of incomplete information. We fill in the gaps by imagining the future.
So consciousness was not raised at this point. But that doesn't mean that it couldn't be an emergent property.
[1] Am at NIPS and attended the speech.
Re: Predictive Learning [pdf]
#15My summary of the slides: to achieve "common sense", Unsupervised Learning is the the next step. Use all information in the data for predicting everything you can including the past. Use adversarial networks to do that.
Re: Predictive Learning [pdf]
#16If page 33 depicts the working of the brain on a very high level, the world model (or simulator) residing inside the agent must contain a model/simulator of the agent itself. Could this give rise to self perception or consiousness?
this is an excellent point. This model has to be recursive and may be depth of recursion has something to do with self-perception?
I don't understand this argument. (It keeps coming up.) The two issues I have with this are:
a) Self-perception does not seem like consciousness to me at all. In meditation, if done properly, there is very little self left. It feels more like pure awareness. It is almost the opposite of the model of the self that the brain constructs.
b) I fail to see how the fact that a mechanism refers to itself should somehow give rise to the feeling of conciousness. Why would it? Nobody would predict consciousness from that if we would not already know it exists and it's easy to imagine a device that has a model of itself and is not self-aware.
I understand the need to somehow fit this into our scientific framework, and the idea that "consciousness is just what it feels to have a brain" is the best thing we have, but I don't think it explains anything. There is something we are missing.
Re: Predictive Learning [pdf]
#17He also presented at CMU Robotics a few weeks ago (and used these slides). Video here: https://youtu.be/IbjF5VjniVE
Re: Predictive Learning [pdf]
#18These slides remind me of the worst PowerPoints ever.
Re: Predictive Learning [pdf]
#19These slides remind me of the worst PowerPoints ever.
Really? They have pictures and everything.