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
91
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
76
Institut seminar 2020
manexagirrezabal
0
35
Automatic Scansion of Poetry (KU)
manexagirrezabal
0
600
RANLP talk
manexagirrezabal
0
74
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
20250624_熊本経済同友会6月例会講演
trafficbrain
1
730
Integrating Static Optimization and Dynamic Nature in JavaScript (GPCE 2025)
tadd
0
110
EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observation and Wikipedia
satai
3
300
Nullspace MPC
mizuhoaoki
1
240
言語モデルの地図:確率分布と情報幾何による類似性の可視化
shimosan
8
2k
ip71_contraflow_reconfiguration
stkmsd
0
110
ロボット学習における大規模検索技術の展開と応用
denkiwakame
1
140
Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation
satai
3
280
なめらかなシステムと運用維持の終わらぬ未来 / dicomo2025_coherently_fittable_system
monochromegane
0
4.3k
MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation
satai
4
370
とあるSREの博士「過程」 / A Certain SRE’s Ph.D. Journey
yuukit
11
4.6k
AWSで実現した大規模日本語VLM学習用データセット "MOMIJI" 構築パイプライン/buiding-momiji
studio_graph
2
820
Featured
See All Featured
Into the Great Unknown - MozCon
thekraken
40
2.1k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
10
900
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Writing Fast Ruby
sferik
630
62k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
46
7.7k
Producing Creativity
orderedlist
PRO
348
40k
Build your cross-platform service in a week with App Engine
jlugia
234
18k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
5.7k
How to Think Like a Performance Engineer
csswizardry
27
2.2k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
54k
Agile that works and the tools we love
rasmusluckow
331
21k
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
10
630
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.