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.

Understanding Convolutional Neural Networks

191 pointsby advanderveeralmost 5 years ago

6 comments

noname123almost 5 years ago
Just a shout-out to Professor Polo (the Professor who is the leader of the Polo Club of Data Science who wrote the tutorial on CNN&#x27;s), 3 years ago, as a CRUD code monkey, I found out about Georgia Tech&#x27;s launching of Online Masters in Data Science on Hacker News and then entered into the program and took Dr.Polo&#x27;s class on Data Visualization and Analysis (for that semester I lit. spent more time on the class than on my day-job)... now for going full circle 3 years later, I see Dr.Polo&#x27;s tutorial on CNN on Hacker News again and am working on CNN&#x2F;RNN&#x27;s for my last class&#x2F;capstone project lol. The circle of life or the circle of HN I suppose!<p>Anyone here in the OMSA&#x2F;OMSCS program?
评论 #23722897 未加载
评论 #23722944 未加载
max_likelihoodalmost 5 years ago
I know very little about CNNs. But, I noticed the ReLu Activation step is Max(0,x) where x is the sum of the pixel intensities from each channel. In this example, it appears x &gt; 0 (for all x) and so the activation step isn&#x27;t really doing much?<p>EDIT: I&#x27;m wrong. x &lt; 0 for some of the pixels. Specifically for the more red-ish channels.
评论 #23722184 未加载
atum47almost 5 years ago
I wrote a nn a while back and made some interesting projects with it. two things I wanted to do: transfer the matrix multiplications to the GPU and also implement convolution layers. if I ever got free time again I&#x27;ll maybe do it.<p>thanks for sharing this, great content. made me think about old projects I have laying around.
lbjalmost 5 years ago
The interactive inspection of each layer is beautifully implemented. I hope that one day we&#x27;ll be able to make even more sense of the consequence of each individual weight, ie. know more than -0.52 for a given pixel.
archerxalmost 5 years ago
Why doesn&#x27;t it explain what the &quot;bias&quot; is?
评论 #23725897 未加载
评论 #23722252 未加载
natchalmost 5 years ago
Very nice interactive tutorial tool. I wish some of the terms were defined. Hyperparameter? Convolution? Kernel?
评论 #23722084 未加载
评论 #23726150 未加载
评论 #23727556 未加载