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.

LSTM: How to Train Neural Networks to Write Like Lovecraft

10 pointsby strikinglooalmost 6 years ago

1 comment

strikinglooalmost 6 years ago
Hey guys, I&#x27;m the writer. As you can see from the post, I&#x27;m still very much learning.<p>What I want the most from this site is for more experienced people to help me out with some of my questions.<p>Here they come:<p>- Can you use Batch Normalization (the one from tf.keras) on an LSTM layer? Or will it break the model?<p>- How do you deal with extremely infrequent words if you do a word-based LSTM (with a one-hot encode of each word in the corpus?)? Do you remove them? Replace them? Cluster them?<p>- Do you think there&#x27;s any other architecture that would&#x27;ve had better results -while still not taking too long to train-?
评论 #20262275 未加载
评论 #20262979 未加载