ICLR and MetaLearning
Apr. 27th, 2020 02:22 pm![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
dmmICLR 2020 is online-only (registration for full participation is a hundred of US units, but a lot of things can be watched for free).
In particular, the video of yesterday's workshop www.betr-rl.ml/2020/ "Beyond “Tabula Rasa” in Reinforcement Learning (BeTR-RL): Agents that remember, adapt, and generalize" is available here:
www.betr-rl.ml/2020/program/
I've seen Jeff Clune's invited talk (very interesting), and also the panel with Jürgen Schmidhuber (reasonably interesting, with him and all 4 invited speakers, that's at about 2:40 in the video; Jeff's talk should be about 3:30 later than the panel).
During the panel, Jeff's remark about advantages of multi-agent architecture was quite interesting for me, and Jürgen made a radical remark that at the end of the day there will be a 10-line program generating advanced super-human AI, and with the benefit of hindsight we'll say that it was obvious and it was strange that we have not found it earlier (I hope I am not distorting his words too much; of course, the first sentence on his website says: "Since age 15 or so, the main goal of professor Jürgen Schmidhuber has been to build a self-improving Artificial Intelligence (AI) smarter than himself, then retire".).
In particular, the video of yesterday's workshop www.betr-rl.ml/2020/ "Beyond “Tabula Rasa” in Reinforcement Learning (BeTR-RL): Agents that remember, adapt, and generalize" is available here:
www.betr-rl.ml/2020/program/
I've seen Jeff Clune's invited talk (very interesting), and also the panel with Jürgen Schmidhuber (reasonably interesting, with him and all 4 invited speakers, that's at about 2:40 in the video; Jeff's talk should be about 3:30 later than the panel).
During the panel, Jeff's remark about advantages of multi-agent architecture was quite interesting for me, and Jürgen made a radical remark that at the end of the day there will be a 10-line program generating advanced super-human AI, and with the benefit of hindsight we'll say that it was obvious and it was strange that we have not found it earlier (I hope I am not distorting his words too much; of course, the first sentence on his website says: "Since age 15 or so, the main goal of professor Jürgen Schmidhuber has been to build a self-improving Artificial Intelligence (AI) smarter than himself, then retire".).
no subject
Date: 2020-05-12 03:51 pm (UTC)https://github.com/anhinga/2020-notes/blob/master/research-drafts/10-lines-thesis.md
no subject
Date: 2020-05-12 03:52 pm (UTC)Assume that there is a moment (now or in the future), where the thesis that approximately 10 lines of sufficiently high-level computer code could generate AI is literally correct. Assume that a good chunk of Internet is available for such a process (although, it's OK to assume that it is a static snapshot of a subset of Internet within a sandbox environment; of course, the question of whether an effective sandbox for such a situation is at all possible is a whole separate long story, long discussion, and long study).
Assume that this chunk of Internet, in particular, contains a fairly large subset of public github, of arxiv, and of wikipedia. The meditation exercise is, then, what these 10 lines of AI-generating code might look like.
This is, obviously, a series of meditation exercises. Each particular exercise depends on your assumptions about the path by which you and/or community arrived at the imagined moment in question.
no subject
Date: 2020-05-12 04:08 pm (UTC)https://en.wikipedia.org/wiki/Group_method_of_data_handling
https://en.wikipedia.org/wiki/Alexey_Ivakhnenko
Schmidhuber says that this was the earliest deep learning work (training an 8-layer net in 1971).