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
82
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
26
NLP for poetry generation and analysis
manexagirrezabal
0
66
Institut seminar 2020
manexagirrezabal
0
28
Automatic Scansion of Poetry (KU)
manexagirrezabal
0
490
RANLP talk
manexagirrezabal
0
70
Defense (Final version)
manexagirrezabal
0
68
Poesiaren eskantsio automatikoa: Bi hizkuntzen azterketa
manexagirrezabal
0
67
CodeFEST literature presentation
manexagirrezabal
0
58
Ongoing work (in mid 2016)
manexagirrezabal
0
20
Other Decks in Research
See All in Research
Weekly AI Agents News! 11月号 論文のアーカイブ
masatoto
0
180
精度を無視しない推薦多様化の評価指標
kuri8ive
1
290
Weekly AI Agents News! 9月号 論文のアーカイブ
masatoto
1
150
[2024.08.30] Gemma-Ko, 오픈 언어모델에 한국어 입히기 @ 머신러닝부트캠프2024
beomi
0
800
TransformerによるBEV Perception
hf149
1
580
文化が形作る音楽推薦の消費と、その逆
kuri8ive
0
200
LLM時代にLabは何をすべきか聞いて回った1年間
hargon24
1
530
多様かつ継続的に変化する環境に適応する情報システム/thesis-defense-presentation
monochromegane
1
590
論文読み会 KDD2024 | Relevance meets Diversity: A User-Centric Framework for Knowledge Exploration through Recommendations
cocomoff
0
110
メタヒューリスティクスに基づく汎用線形整数計画ソルバーの開発
snowberryfield
3
620
20240918 交通くまもとーく 未来の鉄道網編(こねくま)
trafficbrain
0
340
20241115都市交通決起集会 趣旨説明・熊本事例紹介
trafficbrain
0
700
Featured
See All Featured
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
356
29k
It's Worth the Effort
3n
183
28k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
169
50k
Build your cross-platform service in a week with App Engine
jlugia
229
18k
Scaling GitHub
holman
458
140k
A Modern Web Designer's Workflow
chriscoyier
693
190k
How to train your dragon (web standard)
notwaldorf
88
5.7k
Being A Developer After 40
akosma
87
590k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
127
18k
Fashionably flexible responsive web design (full day workshop)
malarkey
405
66k
Why You Should Never Use an ORM
jnunemaker
PRO
54
9.1k
Unsuck your backbone
ammeep
669
57k
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.