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
87
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
29
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
71
CodeFEST literature presentation
manexagirrezabal
0
61
Ongoing work (in mid 2016)
manexagirrezabal
0
23
Other Decks in Research
See All in Research
LLM-as-a-Judge: 文章をLLMで評価する@教育機関DXシンポ
k141303
3
810
Adaptive Experimental Design for Efficient Average Treatment Effect Estimation and Treatment Choice
masakat0
0
130
電通総研の生成AI・エージェントの取り組みエンジニアリング業務向けAI活用事例紹介
isidaitc
1
220
ことばの意味を計算するしくみ
verypluming
11
2.6k
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
430
在庫管理のための機械学習と最適化の融合
mickey_kubo
3
1.1k
クラウドのテレメトリーシステム研究動向2025年
yuukit
3
950
Agentic AIとMCPを利用したサービス作成入門
mickey_kubo
0
240
Cross-Media Information Spaces and Architectures
signer
PRO
0
220
SSII2025 [SS1] レンズレスカメラ
ssii
PRO
2
940
SI-D案内資料_京都文教大学
ryojitakeuchi1116
0
1.6k
MGDSS:慣性式モーションキャプチャを用いたジェスチャによるドローンの操作 / ec75-yamauchi
yumulab
0
230
Featured
See All Featured
A better future with KSS
kneath
239
17k
How to train your dragon (web standard)
notwaldorf
92
6.1k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
233
17k
How GitHub (no longer) Works
holman
314
140k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
507
140k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
181
53k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
Agile that works and the tools we love
rasmusluckow
329
21k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
We Have a Design System, Now What?
morganepeng
53
7.7k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
29
2.7k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
228
22k
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.