Dépôts de carpedm20

carpedm20/jsline-apiCoffeeScript

Line API for JS

Dernier commit 27 janv. 2015

(0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

carpedm20/kaggle-avitoPython

https://www.kaggle.com/c/avito-context-ad-clicks/forums

Dernier commit 23 août 2015

(1 star) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

carpedm20/kakaotalk

KakaoTalk's LOCO protocol for python version

Dernier commit 10 août 2013

(6 stars) (6 forks) (0 issues indexées) (0 good first issues ouvertes)

carpedm20/karelPython

Karel dataset for program synthesis and program induction

Dernier commit 24 déc. 2017

(79 stars) (15 forks) (0 issues indexées) (0 good first issues ouvertes)

carpedm20/kindle

kindle for Python

Aucune donnée de commit récent

(0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

carpedm20/konlpyPython

Python package for Korean natural language processing.

Dernier commit 9 sept. 2014

(0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

carpedm20/korail2Python

Korail (www.letskorail.com) wrapper for Python.

Dernier commit 8 mars 2024

(229 stars) (85 forks) (0 issues indexées) (0 good first issues ouvertes)

carpedm20/korean-japanese-translatorPython

Korean-Japanese translator using word2vec

Dernier commit 21 févr. 2015

(3 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

carpedm20/korean-parallel-corpora

Korean Parallel Corpus

Dernier commit 27 nov. 2014

(0 stars) (0 forks) (0 issues indexées) (0 good first issues ouvertes)

carpedm20/korquad.github.ioCSS

Korean wiki QA dataset for MRC

Dernier commit 18 janv. 2019

(0 stars) (1 fork) (0 issues indexées) (0 good first issues ouvertes)

carpedm20/learningSimpleAlgorithmsLua

We present an approach for learning simple algorithms such as copying, multi-digit addition and single digit multiplication directly from examples. Our framework consists of a set of interfaces, accessed by a controller. Typical interfaces are 1-D tapes or 2-D grids that hold the input and output data. For the controller, we explore a range of neural network-based models which vary in their ability to abstract the underlying algorithm from training instances and generalize to test examples with many thousands of digits. The controller is trained using Q-learning with several enhancements and we show that the bottleneck is in the capabilities of the controller rather than in the search incurred by Q-learning.

Dernier commit 7 déc. 2015