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
97
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
35
NLP for poetry generation and analysis
manexagirrezabal
0
78
Institut seminar 2020
manexagirrezabal
0
38
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
76
CodeFEST literature presentation
manexagirrezabal
0
63
Ongoing work (in mid 2016)
manexagirrezabal
0
25
Other Decks in Research
See All in Research
Attaques quantiques sur Bitcoin : comment se protéger ?
rlifchitz
0
140
それ、チームの改善になってますか?ー「チームとは?」から始めた組織の実験ー
hirakawa51
0
660
ForestCast: Forecasting Deforestation Risk at Scale with Deep Learning
satai
3
390
HoliTracer:Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery
satai
3
620
Sat2City:3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion
satai
4
660
存立危機事態の再検討
jimboken
0
240
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
1.1k
Remote sensing × Multi-modal meta survey
satai
4
710
都市交通マスタープランとその後への期待@熊本商工会議所・熊本経済同友会
trafficbrain
0
120
Proposal of an Information Delivery Method for Electronic Paper Signage Using Human Mobility as the Communication Medium / ICCE-Asia 2025
yumulab
0
170
令和最新技術で伝統掲示板を再構築: HonoX で作る型安全なスレッドフロート型掲示板 / かろっく@calloc134 - Hono Conference 2025
calloc134
0
550
地域丸ごとデイサービス「Go トレ」の紹介
smartfukushilab1
0
920
Featured
See All Featured
Six Lessons from altMBA
skipperchong
29
4.2k
State of Search Keynote: SEO is Dead Long Live SEO
ryanjones
0
120
Have SEOs Ruined the Internet? - User Awareness of SEO in 2025
akashhashmi
0
270
Being A Developer After 40
akosma
91
590k
Fantastic passwords and where to find them - at NoRuKo
philnash
52
3.6k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
Tell your own story through comics
letsgokoyo
1
810
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
162
16k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.4k
How To Stay Up To Date on Web Technology
chriscoyier
791
250k
AI Search: Where Are We & What Can We Do About It?
aleyda
0
7k
Automating Front-end Workflow
addyosmani
1371
200k
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.