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.

Stanford CS231n – Convolutional Neural Networks for Visual Recognition

125 pointsby dennybritzover 10 years ago

4 comments

karpathyover 10 years ago
Hi HN, the course is still in progress so the notes are not yet finished (I&#x27;m currently struggling to finish the ConvNet notes).<p>Our syllabus is here: <a href="http://cs231n.stanford.edu/syllabus.html" rel="nofollow">http:&#x2F;&#x2F;cs231n.stanford.edu&#x2F;syllabus.html</a> where you can also find lecture slides, which have some more information.<p>Lastly, our assignments (that walk you through implementing a Softmax&#x2F;SVM classifier and Neural Networks and ConvNets in Python+numpy) are all on terminal.com. Terminal.com lets us set up a VM in the browser: You visit the assignment URL, fork the snapshot, and you can work right away on the assignment in your browser on an IPython Notebook: the data is there, all dependencies are already installed, and everything ready to go. We&#x27;re also working with terminal.com right now to get access to GPU machines soon, which will let us set up assignments that use Caffe and efficient GPU code, etc.
评论 #9020279 未加载
评论 #9020276 未加载
tim_swover 10 years ago
I&#x27;ve been following along, and this course has been great so far. The author also has made the code for one of his publications about image captioning publicly available: <a href="https://github.com/karpathy/neuraltalk" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;karpathy&#x2F;neuraltalk</a><p>Along with various other nice work about neural networks:<p><a href="http://cs.stanford.edu/people/karpathy/convnetjs/started.html" rel="nofollow">http:&#x2F;&#x2F;cs.stanford.edu&#x2F;people&#x2F;karpathy&#x2F;convnetjs&#x2F;started.htm...</a><p><a href="http://cs.stanford.edu/people/karpathy/recurrentjs/" rel="nofollow">http:&#x2F;&#x2F;cs.stanford.edu&#x2F;people&#x2F;karpathy&#x2F;recurrentjs&#x2F;</a><p><a href="http://karpathy.github.io/neuralnets/" rel="nofollow">http:&#x2F;&#x2F;karpathy.github.io&#x2F;neuralnets&#x2F;</a><p>Nice visualization about classifiers from the class (various svm, softmax):<p><a href="http://vision.stanford.edu/teaching/cs231n/linear-classify-demo/" rel="nofollow">http:&#x2F;&#x2F;vision.stanford.edu&#x2F;teaching&#x2F;cs231n&#x2F;linear-classify-d...</a>
krat0sprakharover 10 years ago
OT: It&#x27;s fantastic that faculty at top universities like Stanford are increasingly making their content freely available on Github. It surely is an awesome time to be alive!
hcarvalhoalvesover 10 years ago
I wish I could take this class online (not an alumnus, not even in the US) but thanks for the free material!