AI & machine learning2014 · shared on Hacker News
One weird trick for parallelizing convolutional neural networks
Explore One weird trick for parallelizing convolutional neural networks, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yjmomarty ·
TensorFlow: open-source library for machine intelligence
1,559 points196 comments
Ywalterbell ·
Building your own deep learning computer is 10x cheaper than AWS
437 points264 comments
Ypaulmd ·
NVIDIA Announces the GeForce GTX 1000 Series
408 points221 comments
Ybobrenjc93 ·
Microsoft Zero and DeepSpeed: Memory Efficient Large Neural Network Training
218 points20 comments
Yracoonear ·
Ask HN: Papers you read in 2015?
193 points45 comments
Yheadalgorithm ·
The Unreasonable Effectiveness of Recurrent Neural Networks (2015)
161 points51 comments
Ybcaulfield ·
Nvidia CEO Reveals New TITAN X at Stanford Deep Learning Meetup
140 points147 comments
Ytodsacerdoti ·
Techniques for Training Large Neural Networks
133 points23 comments
Yingve ·
Making algorithms lock-free with Read-Copy Update (RCU)
121 points57 comments
Yhrb1979 ·
Data Scientist Interviews
65 points29 comments
Yluu ·
ImageNet Large Scale Visual Recognition Competition
50 points14 comments
Yiamtrask ·
Distributing a Fully Connected Neural Network Across a Cluster
30 points6 comments
Ysigna11 ·
One weird trick for parallelizing convolutional neural networks
3 points0 comments