keisuke-umezawa / arxivtimes Goto Github PK
View Code? Open in Web Editor NEWThis project forked from arxivtimes/arxivtimes
repository to research & share the machine learning articles
License: MIT License
This project forked from arxivtimes/arxivtimes
repository to research & share the machine learning articles
License: MIT License
DAATとSAATの経験的比較を行った論文。特に、WAND(DAAT)、BMW(DAAT)、JASS(SAAT)について比較した。この比較は以下の興味深い発見を提供した。
https://cs.uwaterloo.ca/~jimmylin/publications/Crane_etal_WSDM2017.pdf
Matt Crane,1 J. Shane Culpepper,2 Jimmy Lin,1 Joel Mackenzie,2 and Andrew Trotman3
1 David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada
2 Department of Computer Science, RMIT University, Melbourne, Australia
3 Department of Computer Science, University of Otago, Dunedin, New Zealand
Jeff Johnson
Facebook AI Research
New York
Matthijs Douze
Facebook AI Research
Paris
Herve J ´ egou ´
Facebook AI Research
Paris
TensorFlowのようなDeep Learning フレームワークでもプログラミング言語としての意味論は大事。
言語的に体系立てられている必要がある。
Martin Abadi, Michael Isard, and Derek Murray (Google)
roles of semantics in TF
Uncertaiin + explicit assertで確率的なプログラムのテストを書きましょう。
乱数を含むテストはしづらい。確率0.5でtrueになるテストをかけるような仕組みを作る。
http://homes.cs.washington.edu/~djg/papers/mapl17.pdf
Chandrakana Nandi (U. Washington), Dan Grossman (U. Washington), Adrian Sampson (Cornell University), Todd Mytkowicz (Microsoft Research), and Kathryn S. McKinley (Google)
http://theory.stanford.edu/~hawkinsp/papers/pldi12concurrent.pdf
PLDI12 Best Paper
Peter Hawkins
Computer Science Department, Stanford
University
[email protected]
Alex Aiken ∗
Computer Science Department, Stanford
University
[email protected]
Kathleen Fisher †
Computer Science Department, Tufts
University
[email protected]
Martin Rinard
MIT Computer Science and Artificial Intelligence
Laboratory
[email protected]
Mooly Sagiv
Tel-Aviv University
[email protected]
https://theory.stanford.edu/~aiken/publications/papers/pldi11b.pdf
PLDI11
Peter Hawkins
Computer Science Department, Stanford
University
Alex Aiken
Computer Science Department, Stanford University
Kathleen Fisher
Computer Science Department, Tufts University
Martin Rinard
MIT Computer Science and Artificial Intelligence
Laboratory
Mooly Sagiv
Tel-Aviv University
PBE(Programming by Example)とML(Machine Learning)を組み合わせる話。
PBEには以下の要素がある。
PBEにMLを組み込む箇所として以下を提案していた。
http://conf.researchr.org/event/pldi-ecoop-2017/mapl-2017-papers-programming-by-examples-pl-meets-ml
Name: Sumit Gulwani, Microsoft Research
phrase-based SMT(statistical machine learning)をDeep Neural Networkで実現したという論文。
2組のRNNを使うRNN Encoder-Decorderというアーキテクチャを用いており、
Encoderは可変長の入力文字列を固定長のvectorに変換し、Decoderは逆に固定長のvectorから可変長の文字列を生成する。この手法を使うことで従来のphrase-based SMTから性能が大きく向上した。
https://arxiv.org/abs/1406.1078
Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, Yoshua Bengio
University of Montreal
Universite du Maine
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.