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.

Relational Reasoning with Neural Networks

137 pointsby idibidiartistsalmost 8 years ago

7 comments

empath75almost 8 years ago
Can someone go in to more detail about how certain neural networks inherently are able to encode and interpret particular structures? Why RNs capture relations and Recurent neural networks can capture sequential data?
评论 #14498698 未加载
3pt14159almost 8 years ago
I'm not familiar with research on relational reasoning, and the subset they're working with seems pretty well defined, but even so this seems like a pretty meaningful step forward. Can anyone involved in the research comment further on how confident they are that RR is generalizable across dissimilar domains to the one tested?
TFortunatoalmost 8 years ago
Very cool! Not quite the same, but brings to mind SHRDLU, which was recently discussed here.<p>The first few thoughts I had on seeing this: 1) Of course this is by DeepMind! Why would I think anything different. (I love the &quot;basic&quot; research they are doing on NNs &amp; Deep Learning, and am always excited to see a new paper by them).<p>2) I would love to see more investment into this kind of basic ML research. (By that I don&#x27;t mean &quot;easy&quot;, but addressing the fundamentals of how to approach different types &#x2F; classes of problems). A lot of where the DeepMind guys seem to be finding these big wins is in combining &quot;classic&quot; AI &#x2F; CS techniques with Deep Learning &#x2F; Optimization.<p>Examples (And I&#x27;m a novice at deep learning, so someone PLEASE PLEASE correct me if I&#x27;m wrong): AlphaGo - Take a technique like Tree Search for playing a game, and combine with deep networks for the tricky bit of evaluating play positions Deep Reinforcement Learning - Q-Learning and other reinforcement techniques have been around for a while, but they adapted them to a deep neural net architecture Neural Turing Machines - Took a classical model of computation and made it differentiable, alowing for a neural net to &quot;learn&quot; algorithms like sorting. Deep Neural Computing - Figured out how to add and address external memory in a differentiable computer, allowing a neural net to solve problems like path finding on a graph.<p>Where I think a lot of cool stuff is going to continue to come from is by revisiting classic techniques, and figuring out how they can be adapted to a differentiable &#x2F; optimizible architecture. Or taking a classic problem and finding an efficient way to evaluate &quot;goodness&quot; of an answer that lends itself to being used in an optimization problem. Again, not saying it is easy, but I wonder how much &quot;low hanging fruit&quot; there is in revisiting classic algorithms and GOFAI techniques, and asking &quot;can I use this in a Neural Net or adapt this to be differentiable so that I can learn or optimize the tricky bits?&quot;<p>I&#x27;m sure I&#x27;m glossing over a lot &#x2F; missing the point of a lot of it - like I said, just a noob whose super excited about this stuff :-)
评论 #14497363 未加载
albertTJamesalmost 8 years ago
here goes my phd thesis :( They are too fast for a single mind to beat.
评论 #14497081 未加载
评论 #14499232 未加载
MichaelBurgealmost 8 years ago
This looks interesting. I&#x27;d love to train a GAN with relational constraints.
lopatinalmost 8 years ago
Could this be useful for multivariate statistical analysis, such as Basketball Player A has more steals than Player B but only when Player C is on the court? If so, it might get pretty busy on FanDuel
评论 #14510210 未加载
mishurovalmost 8 years ago
Well, it&#x27;s a much more interesting idea than a usual hype article with yet another application of the statistical inference.