What we’re about
Interested in reading some of the classic and newly classic papers in computer science?
This is the Portland, OR chapter of Papers We Love, an organization that curates interesting papers in the computer science literature and helps organize local chapters to read and discuss them.
Prior to each event we will select a paper to read and post it so that attendees can read it in advance to promote good discussion.
At each gathering we will discuss the paper and select the next one to read.
If you know of a great paper we could read, please submit it via GitHub Issues.
You can also join our Discord channel.
Upcoming events (1)
See all- Deep Residual Learning for Image RecognitionThe Glass Lab, Portland, OR
Note: New Location!!
Our next paper is "Deep Residual Learning for Image Recognition" by He, Zhang, Ren, and Sun.
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [41] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the LSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers.
Link: https://arxiv.org/pdf/1512.03385
Afterwards we'll socialize with a drink and a bite somewhere nearby.
We will let you in so please arrive on time. Message us on Discord if no one is at the door.
