Using Machine Learning to Explore Neural Network ArchitecturePhilosophy We strive to create an environment conducive to many different types of research across many different time scales and levels of risk. Learn more about our Philosophy Learn more
Accelerating Deep Learning Research with the Tensor2Tensor Library
As an example of the kind of improvements T2T can offer, we applied the library to machine translation. As you can see in the table above, two different T2T models, SliceNet and Transformer, outperform the previous state-of-the-art, GNMT+MoE. Our best T2T model, Transformer, is 3.8 points better than the standard GNMT model, which itself was 4 points above the baseline phrase-based translation sys
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Revisiting the Unreasonable Effectiveness of Data
The Google Brain Residency Program — One Year Later
Federated Learning: Collaborative Machine Learning without Centralized Training
An Upgrade to SyntaxNet, New Models and a Parsing Competition
Chat Smarter with Allo
Announcing SyntaxNet: The World’s Most Accurate Parser Goes Open Source
Computer, respond to this email.
Sergey and Larry awarded the Seoul Test-of-Time Award from WWW 2015
Google Research Awards: Winter 2014
11 Billion Clues in 800 Million Documents: A Web Research Corpus Annotated with
Fast, Accurate Detection of 100,000 Object Classes on a Single Machine
Excellent Papers for 2012
Syntactic Ngrams over Time
Ngram Viewer 2.0
Machine Learning Book for Students and Researchers