colah / colah.github.io Goto Github PK

View Code? Open in Web Editor NEW

804.0 81.0 190.0 148.37 MB

Home Page: colah.github.io

CSS 7.58% JavaScript 42.39% Shell 0.03% HTML 48.63% SCSS 1.23% TeX 0.14%

colah.github.io's People

Contributors

Stargazers

Watchers

Forkers

lqshixinlei shafiahmed vincentbdb vnijs shjgiser digikata milesqli ajschumacher zhangfaen carolusian jmrinaldi jackdanger gitjd gdb pittacus lgautier dresimpelo badlogicmanpreet sunsided omar-florez muddasani coboosting sitongligit protez sghilas stephanietessier github-io-blog coalabear zhangxinnan sherrysico halisyilboga1 agarwalnaimish vikashkodati michelle190 corbt vyraun dreadlord1984 yochju lapolonio lluisgomez hbcbh1999 luciany garfield2005 brandonmburroughs anddywang caweinshenker phoenixqm yingding zhxsxuan beckettman jyzhang-bjtu hyiltiz raminmh vayel trojany paojianghu hzitoun samithaj cansong1992 lxiong kusl jhorowitz yongyehuang andygoo chenming317 william-lawvere javierlorenzod josevaisman tonydeep pzhao16me nalakawula ferdavid1 engineerkhan utensil-star petrosalema mxochicale berli mrdekk davegeneral sunnycat2013 denysegh ladin157 dawncc galadirith vanlinhnguyen jasonluo-tw owen864720655 ajayku-in handsomeboy yaokeepmoving tomlisankie taylorhxu atinsood isabellepdur dnductien kirankumar-a foodmesh-xyz longlong-jing alishakiba forkacc

colah.github.io's Issues

Confusing sentences for me in "Deep Learning, NLP, and Representations"

Hello, Mr. Olah.

First thing first, thank you for your great work. I am learning with pleasure via your articles.

Here I would like to address what is difficult for me to understand.
The below two sentences are from the source of the section "Shared Representations":

This general tactic ... One of the great strengths of this approach is that it allows the representation to learn from more than one kind of data.

There’s a counterpart to this trick. Instead of learning a way to represent one kind of data and using it to perform multiple kinds of tasks, we can learn a way to map multiple kinds of data into a single representation!

It was kind of confusing for me, because "the trick" and its "counterpart" seem to have the similar descriptions. And below is my current understanding.

For the first one, the representation can learn other kind of data, incrementally, whenever other tasks come in and the word embedding tries to solve the tasks. And for the second one (its counterpart), assuming we already have multiple tasks and its corresponding multiple kinds of data, then the single representation can learn these all data.

Since I have worked this article for the translation in Korean, it would be great if my understanding gets confirmed and corrected.

Best regards,
Don

No automatic redirection from HTTP to HTTPS

colah.github.io has no automatic redirection from HTTP to HTTPS. It should, but until then, please make explicit calls to HTTPS.

Enable RSS feed auto-discovery

Hi! I noticed you have an RSS feed at https://colah.github.io/rss.xml, but it's not linked from anywhere. Please add the following to <head> of each page so that newsreaders could find the feed automatically:

<link rel="alternate" type="application/rss+xml" title="colah's blog" href="rss.xml">

Thank you.

Your figures are too good

Please can you tell me how you made your figures?! Particularly in this post and very specifically this image. Are you using Tikz or something manual?

Thank you for the great blogs.

Wrong labels in LSTM diagram

In Understanding LSTM Networks blog the LSTM diagram has wrong labels this & this image. These are the correct labels:

Change Wording In ConvNet Post

First off, I would just like to say that your blog posts are awesome. The math you are blogging about is extremely complicated (if you are trying to read it via papers) but your posts definitely explain it in Layman's terms better than anything I have come across.

I would change the wording this paragraph from:

"At its most basic, convolutional neural networks can be thought of as a kind of neural network that uses many identical copies of the same neuron.1 This allows the network to have lots of neurons and express computationally large models while keeping the number of actual parameters – the values describing how neurons behave – that need to be learned fairly small."

to something like this

"At its most basic, convolutional neural networks can be thought of as a kind of neural network that uses many identical copies of the same neuron.1 This allows the network to have lots of neurons and express computationally large models while keeping the number of actual parameters (the values describing how neurons behave) that have to be learned fairly small."

I had to read that last sentence a few times to figure out what was going on. This makes more sense to me. Keep up the good work!

hidden state not described in Understanding LSTMs

The hidden state is never described as part of LSTM, and is only mentioned in the section about GRU.
There is a paragraph that refers to both the cell state (C_t) and the hidden state (h_t) as "cell state". This is quite confusing, although the nearby graph provides some insight to what is really meant.

Can I quote your picture about RNN in my paper？

https://camo.githubusercontent.com/90667bfb975db1e7ab28e6a176e722a9820205b2c3d0a912fae312b15477b46f/68747470733a2f2f636f6c61682e6769746875622e696f2f706f7374732f323031352d30382d556e6465727374616e64696e672d4c53544d732f696d672f4c53544d332d7661722d4752552e706e67
The picture you drawed is very fancy. can I use it to introduce RNN in my paper ? Thank you very much.

What tool are you using for drawing recurrent neural network?

Hi, I think the lstm diagrams in your blog are fancy, may I ask what tool did you use to draw them?

Blog Setup

Hello Mr. Olah,

I was going through your blog and really liked the design of the same. I was wondering if you are able to point me to how you set up the same - perhaps a website with instructions or if I can download your repo and try to recreate the same.

Thanks,
RJaikanth

colah / colah.github.io Goto Github PK

colah.github.io's People

Contributors

Stargazers

Watchers

Forkers

colah.github.io's Issues

Confusing sentences for me in "Deep Learning, NLP, and Representations"

No automatic redirection from HTTP to HTTPS

Enable RSS feed auto-discovery

Your figures are too good

Wrong labels in LSTM diagram

Change Wording In ConvNet Post

hidden state not described in Understanding LSTMs

Can I quote your picture about RNN in my paper？

What tool are you using for drawing recurrent neural network?

Blog Setup

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent