Profile cover photo
Profile photo
Deniz Yuret
Deniz's posts

Post has attachment
Overfitting, underfitting, regularization, dropout
Here is an IJulia notebook demonstrating overfitting, underfitting, regularization and dropout in Knet for my machine learning class.

Post has attachment
CharNER: Character-Level Named Entity Recognition
Onur Kuru, Ozan Arkan Can and Deniz Yuret. 2016. COLING . Osaka. ( PDF , Presentation ) Abstract We describe and evaluate a character-level tagger for language-independent Named Entity
Recognition (NER). Instead of words, a sentence is represented as a sequ...

Post has attachment
Learning grammatical categories using paradigmatic representations: Substitute words for language acquisition
Mehmet Ali Yatbaz, Volkan Cirik, Aylin Küntay and Deniz Yuret. 2016. COLING . Osaka. ( PDF , Poster ) Abstract Learning word categories is a fundamental task in language acquisition. Previous studies show
that co-occurrence patterns of preceding and followi...

Post has attachment
Knet: beginning deep learning with 100 lines of Julia (NIPS workshop)
Deniz Yuret. 2016. Machine Learning Systems Workshop at NIPS 2016 . Barcelona. ( PDF , Slide , Poster ) Abstract Knet (pronounced "kay-net") is the Koç University machine learning framework
implemented in Julia, a high-level, high-performance, dynamic progr...

Post has attachment
Transfer Learning for Low-Resource Neural Machine Translation
Zoph, Barret and Yuret, Deniz and May, Jonathan and Knight, Kevin. 2016. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing pp 1568--1575, Austin, Texas. ( PDF ) Abstract The encoder-decoder framework for neural

Post has attachment
Why Neural Translations are the Right Length
Shi, Xing and Knight, Kevin and Yuret, Deniz. 2016. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing pp 2278--2282, Austin, Texas. ( PDF ) Abstract We investigate how neural, encoder-decoder
translation systems outp...

Post has attachment
Beginning deep learning with 500 lines of Julia (20150228)
Click here for a newer version (Knet7) of this tutorial. The code used in this version (KUnet) has been deprecated. There are a number of deep learning packages out there . However most sacrifice readability for efficiency. This has two disadvantages: (1...

Post has attachment
Julia ve Knet ile Derin Öğrenmeye Giriş
ODTÜ Yapay Öğrenme ve Bilgi İşlemede Yeni Teknikler Yaz Okulu, 6-9 Eylül, 2016, ODTÜ, Ankara. ( URL , Sunum )

Post has attachment
Onur Kuru, M.S. 2016
M.S. Thesis: Character-level Tagging. Koç University, Department of Computer Engineering. August, 2016. ( PDF , Presentation ) Abstract: I describe and evaluate a language-independent character-level tagger for sequence
labeling problems: Named Entity Recog...

Post has attachment
AutoGrad.jl is an automatic differentiation package for Julia . It is
a Julia port of the popular Python autograd package. It can
differentiate regular Julia code that includes loops, conditionals,
helper functions, closures etc. by keeping track of the pr...
Wait while more posts are being loaded