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
88
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
30
NLP for poetry generation and analysis
manexagirrezabal
0
70
Institut seminar 2020
manexagirrezabal
0
32
Automatic Scansion of Poetry (KU)
manexagirrezabal
0
580
RANLP talk
manexagirrezabal
0
71
Defense (Final version)
manexagirrezabal
0
72
Poesiaren eskantsio automatikoa: Bi hizkuntzen azterketa
manexagirrezabal
0
72
CodeFEST literature presentation
manexagirrezabal
0
61
Ongoing work (in mid 2016)
manexagirrezabal
0
23
Other Decks in Research
See All in Research
チャッドローン:LLMによる画像認識を用いた自律型ドローンシステムの開発と実験 / ec75-morisaki
yumulab
1
480
心理言語学の視点から再考する言語モデルの学習過程
chemical_tree
2
420
在庫管理のための機械学習と最適化の融合
mickey_kubo
3
1.1k
SSII2025 [TS2] リモートセンシング画像処理の最前線
ssii
PRO
7
2.9k
Self-supervised audiovisual representation learning for remote sensing data
satai
3
230
SSII2025 [TS3] 医工連携における画像情報学研究
ssii
PRO
2
1.2k
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
110
Computational OT #4 - Gradient flow and diffusion models
gpeyre
0
310
クラウドのテレメトリーシステム研究動向2025年
yuukit
3
960
線形判別分析のPU学習による朝日歌壇短歌の分析
masakat0
0
140
Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery
satai
3
490
SkySense : A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery
satai
3
250
Featured
See All Featured
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
48
2.9k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
331
22k
Into the Great Unknown - MozCon
thekraken
40
1.9k
Unsuck your backbone
ammeep
671
58k
Fantastic passwords and where to find them - at NoRuKo
philnash
51
3.3k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
8
690
Why Our Code Smells
bkeepers
PRO
336
57k
A better future with KSS
kneath
238
17k
How to Ace a Technical Interview
jacobian
278
23k
Mobile First: as difficult as doing things right
swwweet
223
9.7k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
138
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.