Sample Room

Weekly readings, essays, field notes, events, and shared resources.

You’re viewing as a guest. Sign in to join in.

Idrisadmin1h

Which book should we read next month after we finish the current packet?

Poll · pick any that work

IdrisadminJul 22

Field notes

A few things worth keeping from this week, mostly unedited.

The light in the front room, four o'clock.
That thing Wren said about the tide.
The paper everyone should actually read: Attention Is All You Need

Small pages, kept small — that's the whole idea.

not everything needs a caption
some of it just needs to be kept

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, et al.

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the…

IdrisadminJul 21

Reading group pick for next week?

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, et al.

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the…