TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Consensus Learning in AI Systems

1 pointsby dalyabout 2 years ago
In Geoffrey Hinton&#x27;s Cambridge discussion[0] he makes the argument that self-learning systems could share their weights among many other copies. I refer to this as &quot;consensus learning&quot;.<p>I think this relies on the flawed assumption that weights can be shared. Consider two systems, e.g. robots, that are working on a task, such as one I&#x27;m familiar with, tightening lugnuts when changing a tire. Each robot is not EXACTLY like any other. When learning a &quot;tacit knowledge&quot; task, each robot will have different feedback due to such items as wear in the joints. The updated weights in each system diverges, even on the same task.<p>Even in knowledge-only tasks, if each system is trying to learn and they are in different environments (e.g. reading books), they will develop weights that are local. Given a dozen robots reading books in parallel it is not at all clear how their weights could be combined.<p>Consider robots reading philosophy books or mathematics books. They will encounter &#x27;definitions&#x27; which have subtle or maybe not-so-subtle differences (e.g. satire). Even such obvious ideas as &quot;parallel&quot; lines can be a source of definitional argument. These new definitions change the mapping in your Word2Vec, effectively changing the very basis of the systems knowledge map.<p>I ran into this issue when working on Expert Systems years ago. Expert Systems that kept extensive state which differed based on the environment of their use would get &quot;confused&quot; when importing a rule developed elsewhere by a different &quot;expert&quot;.<p>It is my conjecture that any system that remembers and acts on prior knowledge cannot reliably engage in consensus learning schemes. The new knowledge has to be abstracted and taught.<p>This is the reason we need to teach. We have to abstract over our knowledge and extract the high level goal states we wish to communicate. Students need to self-adapt to these goal states.<p>You might disagree but methinks that proves the point. :-)<p>[0] https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=sitHS6UDMJc

no comments

no comments