If change processes can be learned/extracted from predictive coherence and/or explicit creation via social teaching, and predictive coherence is the basis of powerful language models like BERT and GPT-n, what would a social teaching language model look like and how successful could it be? Off the top of my head, I can't think of any examples ... do you know of any? Do we have the hardware (or the person-power) to create such a model?
Perhaps it's because this post has a strong sense of motion due to its subject matter, but this was particularly engaging, bravo!
Glad you liked it. As for social learning, I think it comes back to imitation from the very start. I've got plans to get to that subject, but it's still a long way off: I have to complete a description of perception, describe the behavioral system, and then handle episodic formation and narratives. Only then do I plan to turn to the topic of acquisition and adaptation, which will require descending into a description of the social instinct, that is, the instinct toward imitation, which requires a fundamental attraction towards other people and the ability to rank who and what is to be imitated. I think the answers to your questions lie in those systems.
I guess what I'm saying is that social teaching is based on so many building blocks, that it's hard to simulate piecemeal. There are a lot of people working on social learning models. Cynthia Brazeal comes to mind, and there's Regina Barzilay as well, who works on language in robots as a social model.
If change processes can be learned/extracted from predictive coherence and/or explicit creation via social teaching, and predictive coherence is the basis of powerful language models like BERT and GPT-n, what would a social teaching language model look like and how successful could it be? Off the top of my head, I can't think of any examples ... do you know of any? Do we have the hardware (or the person-power) to create such a model?
Perhaps it's because this post has a strong sense of motion due to its subject matter, but this was particularly engaging, bravo!
Glad you liked it. As for social learning, I think it comes back to imitation from the very start. I've got plans to get to that subject, but it's still a long way off: I have to complete a description of perception, describe the behavioral system, and then handle episodic formation and narratives. Only then do I plan to turn to the topic of acquisition and adaptation, which will require descending into a description of the social instinct, that is, the instinct toward imitation, which requires a fundamental attraction towards other people and the ability to rank who and what is to be imitated. I think the answers to your questions lie in those systems.
I guess what I'm saying is that social teaching is based on so many building blocks, that it's hard to simulate piecemeal. There are a lot of people working on social learning models. Cynthia Brazeal comes to mind, and there's Regina Barzilay as well, who works on language in robots as a social model.