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.

Vector-based navigation using grid-like representations in artificial agents

21 pointsby stirbotabout 7 years ago

2 comments

aplabout 7 years ago
It&#x27;s certainly an interesting paper, but there&#x27;s a bit of publication weirdness at play here.<p>In October &#x27;17, Cueva &amp; Wei put out a(n anonymous) paper that recapitulates the core result almost exactly -- that training a recurrent neural network to perform dead reckoning&#x2F;path integration gives you intermediate units whose place fields strongly resemble grid cells. Critically, this only happens when regularization is applied; Cueva&#x2F;Wei used noisy inputs and DeepMind implemented 50% stochastic dropout in the intermediate linear layer. There are some superficial differences (generic RNN units vs. LSTM), but at their core these studies are virtually identical. Check it out:<p><a href="https:&#x2F;&#x2F;openreview.net&#x2F;forum?id=B17JTOe0-" rel="nofollow">https:&#x2F;&#x2F;openreview.net&#x2F;forum?id=B17JTOe0-</a><p>What I don&#x27;t get -- why doesn&#x27;t DeepMind acknowledge this result? Sure, the Nature paper was submitted in July &#x27;17, but these things go through many revisions. Clearly, DeepMind went a bit further with the whole integrating visual CNNs&#x2F;grid cells part. Nonetheless: Fig. 1 is the core result, everything from Fig. 2 onwards is nice-to-have but not essential, and I feel like Cueva&#x2F;Wei got there first.<p>Ah, well. At least the minor controversy brings in great publicity for the Cueva&#x2F;Wei paper.
stirbotabout 7 years ago
Nature news article on the paper: <a href="https:&#x2F;&#x2F;www.nature.com&#x2F;articles&#x2F;d41586-018-04992-7" rel="nofollow">https:&#x2F;&#x2F;www.nature.com&#x2F;articles&#x2F;d41586-018-04992-7</a>