Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification · HackerPapers discussions

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — mentioned by peterfirefly

Fri, 22 Dec 2023 23:48:21 GMT

Not necessarily. It turns out to really matter how the weights are initialized (randomly, but from which distribution?) for ordinary feed-forward neural nets that only uses standard neurons -- different activation functions have different optimal initialization distributions. https://machinelearningmastery.com/weight-initialization-for... A big breakthrough was Kaiming He's work on initialization for ReLU: https://arxiv.org/abs/1502.01852 (Kaiming is the personal name, He is the family name. He Kaiming is the native Chinese order. Lots of citations use "Kaiming" by mistake.)

Paper and discussion history. A mention is not an endorsement.

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — mentioned by kahnjw

Sun, 03 May 2020 22:16:54 GMT

Words matter, concretely define "open ended"? Did you just add that phrase to preemptively nullify evidence to the contrary? Deep learning has surpassed human level performance on many tasks [1][2]... (could add more you get the point). [1] https://www.sciencedirect.com/science/article/pii/S2215017X1... [2] https://arxiv.org/pdf/1502.01852v1.pdf

Paper and discussion history. A mention is not an endorsement.

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — mentioned by tanilama

Tue, 14 Nov 2017 07:25:52 GMT

https://arxiv.org/abs/1512.03385 Deep Residual Learning for Image Recognition Citation 4000+. Milestone of image recognition. https://arxiv.org/abs/1502.01852 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Also known as PreLU, citation 1600+. The initialization scheme is widely adapted by a lot of following works. Those are the most influential ones, all come from Kaiming He. He is now in FAIR, and keeps very good publication record, with works like MASK-RCNN, but that doesn't really count as purely Chinese contribution, so we skipped here. Some…

Paper and discussion history. A mention is not an endorsement.

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — mentioned by xiphias

Thu, 20 Oct 2016 12:11:12 GMT

Researchers already passed human level image classification performance in 2015. https://arxiv.org/pdf/1502.01852.pdf

Paper and discussion history. A mention is not an endorsement.

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — mentioned by abrichr

Mon, 14 Dec 2015 04:41:43 GMT

Human level performance was surpassed earlier this year: http://arxiv.org/abs/1502.01852

Paper and discussion history. A mention is not an endorsement.

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — mentioned by lars

Sat, 14 Feb 2015 09:12:31 GMT

Since this paper along with [1] both beat human level performance on ImageNet, using seemingly unrelated techniques, it seems like there's a clear path to achieve the next state of the art result: Implement and train a network that uses both Batch Normalization and PReLU's at the same time. Right? 1: http://arxiv.org/pdf/1502.01852v1.pdf

Paper and discussion history. A mention is not an endorsement.

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — HN submission

Mon, 09 Feb 2015 18:50:43 GMT

Surpassing Human-Level Performance on ImageNet Classification [pdf]

53 points; 13 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — HN submission

Mon, 09 Feb 2015 05:30:45 GMT

Surpassing Human-Level Performance on ImageNet Classification

9 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.