Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Char-rnn aurkezpena
Search
Manex Agirrezabal
March 14, 2016
Research
100
0
Share
Char-rnn aurkezpena
Manex Agirrezabal
March 14, 2016
More Decks by Manex Agirrezabal
See All by Manex Agirrezabal
The Flipped Classroom model for teaching Conditional Random Fields in an NLP course
manexagirrezabal
0
37
NLP for poetry generation and analysis
manexagirrezabal
0
79
Institut seminar 2020
manexagirrezabal
0
39
Automatic Scansion of Poetry (KU)
manexagirrezabal
0
670
RANLP talk
manexagirrezabal
0
78
Defense (Final version)
manexagirrezabal
0
74
Poesiaren eskantsio automatikoa: Bi hizkuntzen azterketa
manexagirrezabal
0
78
CodeFEST literature presentation
manexagirrezabal
0
65
Ongoing work (in mid 2016)
manexagirrezabal
0
28
Other Decks in Research
See All in Research
[Devfest Incheon 2025] 모두를 위한 친절한 언어모델(LLM) 학습 가이드
beomi
2
1.5k
[IBIS 2025] 深層基盤モデルのための強化学習驚きから理論にもとづく納得へ
akifumi_wachi
20
9.9k
はじまりの クエスチョンブック —余暇と豊かさにあふれた社会とは?
culturaltransition
PRO
0
240
Tiaccoon: Unified Access Control with Multiple Transports in Container Networks
hiroyaonoe
0
1.3k
IEEE AIxVR 2026 Keynote Talk: "Beyond Visibility: Understanding Scenes and Humans under Challenging Conditions with Diverse Sensing"
miso2024
0
140
ブレグマン距離最小化に基づくリース表現量推定:バイアス除去学習の統一理論
masakat0
0
210
姫路市 -都市OSの「再実装」-
hopin
0
1.7k
量子コンピュータの紹介
oqtopus
0
260
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
440
【SIGGRAPH Asia 2025】Lo-Fi Photograph with Lo-Fi Communication
toremolo72
0
140
「行ける・行けない表」による地域公共交通の性能評価
bansousha
0
130
視覚から身体性を持つAIへ: 巧緻な動作の3次元理解
tkhkaeio
1
230
Featured
See All Featured
How to Get Subject Matter Experts Bought In and Actively Contributing to SEO & PR Initiatives.
livdayseo
0
92
How to build a perfect <img>
jonoalderson
1
5.3k
The Illustrated Guide to Node.js - THAT Conference 2024
reverentgeek
1
320
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.4k
The Pragmatic Product Professional
lauravandoore
37
7.2k
Breaking role norms: Why Content Design is so much more than writing copy - Taylor Woolridge
uxyall
0
240
Leveraging LLMs for student feedback in introductory data science courses - posit::conf(2025)
minecr
1
210
SEOcharity - Dark patterns in SEO and UX: How to avoid them and build a more ethical web
sarafernandez
0
160
The AI Search Optimization Roadmap by Aleyda Solis
aleyda
1
5.5k
How to Grow Your eCommerce with AI & Automation
katarinadahlin
PRO
1
160
Reflections from 52 weeks, 52 projects
jeffersonlam
356
21k
Building a Scalable Design System with Sketch
lauravandoore
463
34k
Transcript
Poesiaren metrika DL bidez Manex Agirrezabal https://github.com/manexagirrezabal/char-rnn/
Proba ezberdinak TensorFlow: Sequence-to-sequence models https://www.tensorflow.org/versions/master/tutorials/seq2seq/index.html Torch: char-rnn (Andrew Karpathy)
https://github.com/karpathy/char-rnn/
Char-rnn http://karpathy.github.io/2015/05/21/rnn-effectiveness/ Karaktere mailako hizkuntz-ereduak sortzeko balio du. Sarrera gisa
testu hutsa.
Char-rnn Gure beharretarako moldatu behar: to swell the gourd and
plump the ha zel shells - ' - ' - ' - ' - ' wo man much missed how you call to me call to me ' - - ' - - ' - - ' - -
Char-rnn Dataset-a testu soil gisa: To_= swell_+ the_= gourd_+ and_=
plump_+ the_= ha_+ zel_= shells_+ To_= swell_+ the_= gourd_+ and_= plump_+ the_= hazel_+= shells_+ Wo_+ man_= much_= missed_+ how_= you_= call_+ to_= me_= call_+ to_= me_= Woman_+= much_= missed_+ how_= you_= call_+ to_= me_= call_+ to_= me_=
Char-rnn (training) $ th train.lua Parametroak: Model: [RNN, LSTM edo
GRU] rnn_size: LSTMaren (zelda) barruko tamaina num_layers: LSTMaren kapa kopurua seq_length: sekuentzian ikasteko karaktere kopurua
Char-rnn (prediction) $ th sample(mod).lua Parametroak: Model: eredu entrenatua Primetext:
sarrera testua (_ karakterearekin amaituta)
Char-rnn (prediction) Python programa bat (callSampleMod.py) aurreko programari deitzeko pausuz
pausu: $ th sampleMod.lua model M1 primetext “to_” = $ th sampleMod.lua model M1 primetext “to_= swell_” + $ th sampleMod.lua model M1 primetext “to_= swell_+ the_” = ...
Char-rnn (prediction) Arazoa: Hasieran, informazio gutxi duenez, batzuetan hanka sartzen
(+ propagatzen) du predikzioan. Adibidez, “to_” sarrerarekin Horrentzako soluzioa, predikzioa bi aldetara egitea.
Char-rnn (FW) Parametroak optimizatu nahi ditugu (seq_length, batch_size, rnn_size, ...)
Embedding-ak erabili nahi ditugu, baina gure hipotesia da ez dutela asko lagunduko.