Learning Transferable Architectures for Scalable Image Recognition · HackerPapers discussions

Learning Transferable Architectures for Scalable Image Recognition — mentioned by cweill

Tue, 30 Oct 2018 19:26:15 GMT

We have an example of AdaNet on GitHub that uses several complex CNN layers (conv2d, pooling, linearly-separable layers) as part of the NASNet-A architecture (presented in https://arxiv.org/abs/1707.07012): https://github.com/tensorflow/adanet/blob/master/adanet/exam... AdaNet supports high level APIs (e.g tf.layers, tf.losses), so it can support RNN cells as well.

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

Learning Transferable Architectures for Scalable Image Recognition — mentioned by kripke

Fri, 13 Jul 2018 18:55:47 GMT

Not GP, but you are probably looking for the "Neural Architecture Search" series [1] [2] [3]. First one uses something like 1k GPUs for a month, next one is a bit more reasonable, and the last one actually has a reasonable training time, and has comparable performance to DARTS (see ENAS in comparison tables). 1: https://arxiv.org/abs/1611.01578 2: https://arxiv.org/abs/1707.07012 3: https://arxiv.org/abs/1802.03268

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

Learning Transferable Architectures for Scalable Image Recognition — mentioned by rkaplan

Mon, 06 Nov 2017 08:58:28 GMT

This is not "AI that builds AI". The actual research behind AutoML is called NASNet (https://arxiv.org/pdf/1707.07012.pdf), and all it is simply: we found two good neural network layers (called NASNet normal cells / reduction cells in the paper) that work well on many different image datasets. It's a very cool research result. But it's not something that will replace AI researchers.

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

Learning Transferable Architectures for Scalable Image Recognition — HN submission

Mon, 11 Sep 2017 15:26:05 GMT

Machine learning optimization of machine learning architecture

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

Learning Transferable Architectures for Scalable Image Recognition — mentioned by paulsutter

Sat, 02 Sep 2017 22:33:52 GMT

Practical example, neural architecture search to discover convnets that require less computation, https://arxiv.org/abs/1707.07012 "Learning Transferable Architectures for Scalable Image Recognition"

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

Learning Transferable Architectures for Scalable Image Recognition — mentioned by hedgehog

Mon, 21 Aug 2017 05:48:52 GMT

This is good background but modern architecture are significantly better: Learning Transferable Architectures for Scalable Image Recognition https://arxiv.org/abs/1707.07012

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

Learning Transferable Architectures for Scalable Image Recognition — HN submission

Mon, 31 Jul 2017 15:32:42 GMT

Learning Transferable Architectures for Scalable Image Recognition

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

Learning Transferable Architectures for Scalable Image Recognition — HN submission

Thu, 27 Jul 2017 00:00:27 GMT

Learning Transferable Architectures for Scalable Image Recognition

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