TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

The Bongard Problems

30 点作者 vardhanw将近 9 年前

5 条评论

rdtsc将近 9 年前
This is very neat. Besides this site and these results (updated till 2006):<p><a href="http:&#x2F;&#x2F;www.foundalis.com&#x2F;res&#x2F;solvprog.htm" rel="nofollow">http:&#x2F;&#x2F;www.foundalis.com&#x2F;res&#x2F;solvprog.htm</a><p>Anyone know if since then, say using deep learning or other newer methods, these problems are solvable easier?<p>I like the idea behind this, perhaps being able to solve these would be a stepping stone before solving the Turing test. And I think this kind of stuff points to developing a general AI.<p>The background of this is very interesting. The author of this research has stopped working on the problem for ethical reasons:<p><a href="http:&#x2F;&#x2F;www.foundalis.com&#x2F;soc&#x2F;why_no_more_Bongard.html" rel="nofollow">http:&#x2F;&#x2F;www.foundalis.com&#x2F;soc&#x2F;why_no_more_Bongard.html</a><p>&quot;If this is achieved, eventually intelligent weapons of mass destruction will be built, without doubt. That’s what I would like to explain below.&quot;<p>I don&#x27;t want to comment on that or qualify it in any way (I do have some thoughts about it, but would rather not share them). Will just say it was an interesting find.<p>Also learned about Mikhail Bongard, a Soviet machine learning researcher from the 60s-70s -- <a href="http:&#x2F;&#x2F;www.foundalis.com&#x2F;res&#x2F;Mikhail_Moiseevich_Bongard.html" rel="nofollow">http:&#x2F;&#x2F;www.foundalis.com&#x2F;res&#x2F;Mikhail_Moiseevich_Bongard.html</a> for some reason I imagined that part of the world simply did not have any background or interest in that discipline at that time, so it is interesting to learn something new there too.
vardhanw将近 9 年前
The OP is about the authors research into the BPs as a means to reason about cognition. Originated by the russian scientist in 1967 and used and expanded by D. Hofstaedter in GEB. Here&#x27;s [1] an index to all the BPs till now, and here&#x27;s [2] the authors ideas on cognition which were developed in his research. Interesting that the research was abandoned [3] earlier based on ethical concerns of the possible misuse of AI. There is also a programmatic implementation of a BP solver.<p>[Edit]* this comment was not posted for a while, there is already another one with similar and more details now.<p>[1] <a href="http:&#x2F;&#x2F;www.foundalis.com&#x2F;res&#x2F;bps&#x2F;bpidx.htm" rel="nofollow">http:&#x2F;&#x2F;www.foundalis.com&#x2F;res&#x2F;bps&#x2F;bpidx.htm</a><p>[2] <a href="http:&#x2F;&#x2F;www.foundalis.com&#x2F;res&#x2F;poc&#x2F;PrinciplesOfCognition.htm" rel="nofollow">http:&#x2F;&#x2F;www.foundalis.com&#x2F;res&#x2F;poc&#x2F;PrinciplesOfCognition.htm</a><p>[3] <a href="http:&#x2F;&#x2F;www.foundalis.com&#x2F;soc&#x2F;why_no_more_Bongard.html" rel="nofollow">http:&#x2F;&#x2F;www.foundalis.com&#x2F;soc&#x2F;why_no_more_Bongard.html</a>
fernly将近 9 年前
Boy does this make me feel stupid. Pattern puzzles in IQ tests are always the hardest for me. The first, &quot;trivial&quot; example stumped me...
评论 #12067894 未加载
评论 #12065142 未加载
评论 #12064566 未加载
numlocked将近 9 年前
Is the &quot;hard&quot; one that the shapes on the left all have &gt;=50% of their sides as single, straight lines? I&#x27;ve never die these types of problems before so totally unsure if I stumbled on an answer quickly, or don&#x27;t understand what defines a solution.
评论 #12064630 未加载
00098345将近 9 年前
Interesting tidbit: The author&#x27;s PhD advisor is the author of the celebrated text &quot;Godel, Escher, Bach&quot;.