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.

An Introduction to Recurrent Neural Networks

281 pointsby bibytealmost 6 years ago

7 comments

stereolambdaalmost 6 years ago
It&#x27;s worth noting that apparently (as I learned lately) RNNs are going slightly out of fashion because they are hard to parallelize and have trouble remembering important stuff at larger distances. Transformers are proposed as a possible solution - very roughly speaking, they use attention mechanisms instead of recurrent memory and can run in parallel.<p>I have to say that while I understand the problems with recurrent nets (which I&#x27;ve used many times), I haven&#x27;t yet grokked the alternatives. Here are some decently looking search results for you as starting points. Warning, these can be longer and heavier reads probably not for beginners.<p><a href="https:&#x2F;&#x2F;towardsdatascience.com&#x2F;the-fall-of-rnn-lstm-2d1594c74ce0" rel="nofollow">https:&#x2F;&#x2F;towardsdatascience.com&#x2F;the-fall-of-rnn-lstm-2d1594c7...</a> (there&#x27;s some sensationalism here to be fair)<p><a href="https:&#x2F;&#x2F;mchromiak.github.io&#x2F;articles&#x2F;2017&#x2F;Sep&#x2F;12&#x2F;Transformer-Attention-is-all-you-need&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mchromiak.github.io&#x2F;articles&#x2F;2017&#x2F;Sep&#x2F;12&#x2F;Transformer...</a><p><a href="https:&#x2F;&#x2F;www.analyticsvidhya.com&#x2F;blog&#x2F;2019&#x2F;06&#x2F;understanding-transformers-nlp-state-of-the-art-models&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.analyticsvidhya.com&#x2F;blog&#x2F;2019&#x2F;06&#x2F;understanding-t...</a><p><a href="https:&#x2F;&#x2F;www.tensorflow.org&#x2F;beta&#x2F;tutorials&#x2F;text&#x2F;transformer" rel="nofollow">https:&#x2F;&#x2F;www.tensorflow.org&#x2F;beta&#x2F;tutorials&#x2F;text&#x2F;transformer</a><p>That being said, I think that understanding RNNs is very beneficial conceptually and nowadays there are relatively easy to use implementations that should be pretty good for many use cases.
评论 #20529604 未加载
评论 #20531267 未加载
评论 #20528777 未加载
vzhou842almost 6 years ago
Hey, author here. Happy to answer any questions or take any suggestions.<p>Runnable code from the article: <a href="https:&#x2F;&#x2F;repl.it&#x2F;@vzhou842&#x2F;A-RNN-from-scratch" rel="nofollow">https:&#x2F;&#x2F;repl.it&#x2F;@vzhou842&#x2F;A-RNN-from-scratch</a>
评论 #20526925 未加载
评论 #20525519 未加载
评论 #20527583 未加载
评论 #20530665 未加载
wish5031almost 6 years ago
Nice! I like that the author wrote the code by hand rather than leaning on some framework. It makes it a lot easier to connect the math to the code. :)<p>As a meta-comment on these &quot;Introduction to _____ neural network&quot; articles (not just this one), I wish people would spend more time talking about when their neural net isn&#x27;t the right tool for the job. SVMs, kNN, even basic regression techniques aren&#x27;t any less effective than they were 20 years ago. They&#x27;re easier to interpret and debug, require many fewer parameters, and potentially (you may need to apply some tricks here or there) faster at both training and evaluation time.
cheezalmost 6 years ago
This kind of article is absolutely the thing everyone new to deep learning&#x2F;neural networks should read. I wish there was one for each type of algorithm.
评论 #20527647 未加载
rrggrralmost 6 years ago
Would be great if you showed the final output (eg. semantic analysis) result.
mleventalalmost 6 years ago
why do people insist on mentioning the bias terms in expository essays? it&#x27;s a detail that clutters the equations. why not keep the transformations linear and then at the end make a note that you also need to shift using a bias term.
ape4almost 6 years ago
I doubt Google Translate uses RNN. They use Statistical Machine Translation. Oops, I see they switched to NN in 2016. <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Google_Translate" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Google_Translate</a>
评论 #20526094 未加载
评论 #20530885 未加载