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
0
90
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
33
NLP for poetry generation and analysis
manexagirrezabal
0
71
Institut seminar 2020
manexagirrezabal
0
34
Automatic Scansion of Poetry (KU)
manexagirrezabal
0
590
RANLP talk
manexagirrezabal
0
73
Defense (Final version)
manexagirrezabal
0
73
Poesiaren eskantsio automatikoa: Bi hizkuntzen azterketa
manexagirrezabal
0
73
CodeFEST literature presentation
manexagirrezabal
0
62
Ongoing work (in mid 2016)
manexagirrezabal
0
24
Other Decks in Research
See All in Research
日本語新聞記事を用いた大規模言語モデルの暗記定量化 / LLMC2025
upura
0
180
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
0
160
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
kurita
0
170
引力・斥力を制御可能なランダム部分集合の確率分布
wasyro
0
240
集合間Bregmanダイバージェンスと置換不変NNによるその学習
wasyro
0
140
GPUを利用したStein Particle Filterによる点群6自由度モンテカルロSLAM
takuminakao
0
250
PhD Defense 2025: Visual Understanding of Human Hands in Interactions
tkhkaeio
1
190
IMC の細かすぎる話 2025
smly
2
620
AIによる画像認識技術の進化 -25年の技術変遷を振り返る-
hf149
7
4k
Vision and LanguageからのEmbodied AIとAI for Science
yushiku
PRO
1
530
Agentic AIとMCPを利用したサービス作成入門
mickey_kubo
0
530
Delta Airlines® Customer Care in the U.S.: How to Reach Them Now
bookingcomcustomersupportusa
0
110
Featured
See All Featured
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
8
920
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
358
30k
Build The Right Thing And Hit Your Dates
maggiecrowley
37
2.9k
Building an army of robots
kneath
306
46k
jQuery: Nuts, Bolts and Bling
dougneiner
64
7.9k
Become a Pro
speakerdeck
PRO
29
5.5k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
112
20k
Thoughts on Productivity
jonyablonski
70
4.8k
Reflections from 52 weeks, 52 projects
jeffersonlam
352
21k
Java REST API Framework Comparison - PWX 2021
mraible
33
8.8k
Rebuilding a faster, lazier Slack
samanthasiow
83
9.2k
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.