Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Char-rnn aurkezpena
Search
Manex Agirrezabal
March 14, 2016
Research
120
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
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
61
NLP for poetry generation and analysis
manexagirrezabal
0
98
Institut seminar 2020
manexagirrezabal
0
47
Automatic Scansion of Poetry (KU)
manexagirrezabal
0
690
RANLP talk
manexagirrezabal
0
86
Defense (Final version)
manexagirrezabal
0
100
Poesiaren eskantsio automatikoa: Bi hizkuntzen azterketa
manexagirrezabal
0
92
CodeFEST literature presentation
manexagirrezabal
0
74
Ongoing work (in mid 2016)
manexagirrezabal
0
34
Other Decks in Research
See All in Research
AI創薬の壁
kanojikajino
1
1.2k
OWASP AISVS - C7
shiell
2
860
[WebDB2026]セレンディピティ指向推薦システム再考 ―セレンディピティの原義・類型・発生過程に基づく設計指針―
recsyslab
PRO
0
230
MIRU2026 チュートリアル講演2:三次元データ処理の動向
nnchiba
8
5.5k
A new deal for disabled people
resolutionfoundation
0
370
Empreinte carbone des ovins : une approche globale (technique, économique, environnementale) – 4 années de résultats avec LIFE GREEN SHEEP
institutdelelevage
PRO
0
150
VLMの推論を高速化する視覚トークン削減の仕組み
tattaka
2
420
TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis
satai
3
130
Who’s Behind the Divide?
sirmatrixpage
1
1.5k
山中市政の総括:相反する二つの顔
sishi
0
230
Développer des solutions de réduction des émissions de méthane entérique : 1ers résultats Méthane 2030
institutdelelevage
PRO
0
290
La longévité des troupeaux laitiers: état des lieux et perspectives
institutdelelevage
PRO
0
140
Featured
See All Featured
Deep Space Network (abreviated)
tonyrice
0
410
My Coaching Mixtape
mlcsv
0
380
The Hidden Cost of Media on the Web [PixelPalooza 2025]
tammyeverts
2
580
New Earth Scene 8
popppiees
5
2.8k
エンジニアに許された特別な時間の終わり
watany
109
250k
A Soul's Torment
seathinner
9
3.9k
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.6k
SEO for Brand Visibility & Recognition
aleyda
0
4.9k
Paper Plane (Part 1)
katiecoart
PRO
3
12k
Building Adaptive Systems
keathley
44
3.3k
The Spectacular Lies of Maps
axbom
PRO
1
1.1k
Stop Working from a Prison Cell
hatefulcrawdad
274
21k
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.