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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Manex Agirrezabal
March 14, 2016
Research
0
99
Char-rnn aurkezpena
Manex Agirrezabal
March 14, 2016
Tweet
Share
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
36
NLP for poetry generation and analysis
manexagirrezabal
0
78
Institut seminar 2020
manexagirrezabal
0
39
Automatic Scansion of Poetry (KU)
manexagirrezabal
0
660
RANLP talk
manexagirrezabal
0
77
Defense (Final version)
manexagirrezabal
0
74
Poesiaren eskantsio automatikoa: Bi hizkuntzen azterketa
manexagirrezabal
0
78
CodeFEST literature presentation
manexagirrezabal
0
63
Ongoing work (in mid 2016)
manexagirrezabal
0
27
Other Decks in Research
See All in Research
Ankylosing Spondylitis
ankh2054
0
150
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
260
教師あり学習と強化学習で作る 最強の数学特化LLM
analokmaus
2
940
データサイエンティストをめぐる環境の違い2025年版〈一般ビジネスパーソン調査の国際比較〉
datascientistsociety
PRO
0
920
A History of Approximate Nearest Neighbor Search from an Applications Perspective
matsui_528
1
190
生成的情報検索時代におけるAI利用と認知バイアス
trycycle
PRO
0
380
湯村研究室の紹介2025 / yumulab2025
yumulab
0
320
製造業主導型経済からサービス経済化における中間層形成メカニズムのパラダイムシフト
yamotty
0
510
量子コンピュータの紹介
oqtopus
0
230
AIスーパーコンピュータにおけるLLM学習処理性能の計測と可観測性 / AI Supercomputer LLM Benchmarking and Observability
yuukit
1
730
2026年1月の生成AI領域の重要リリース&トピック解説
kajikent
0
810
生成AI による論文執筆サポート・ワークショップ 論文執筆・推敲編 / Generative AI-Assisted Paper Writing Support Workshop: Drafting and Revision Edition
ks91
PRO
0
150
Featured
See All Featured
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
3.4k
DevOps and Value Stream Thinking: Enabling flow, efficiency and business value
helenjbeal
1
140
Rails Girls Zürich Keynote
gr2m
96
14k
Product Roadmaps are Hard
iamctodd
PRO
55
12k
Odyssey Design
rkendrick25
PRO
2
540
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
199
73k
What Being in a Rock Band Can Teach Us About Real World SEO
427marketing
0
190
Stewardship and Sustainability of Urban and Community Forests
pwiseman
0
140
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.5k
Leadership Guide Workshop - DevTernity 2021
reverentgeek
1
230
The Limits of Empathy - UXLibs8
cassininazir
1
250
Unsuck your backbone
ammeep
672
58k
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.