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
75
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
能動適応的実験計画
masakat0
2
840
不確実性下における目的と手段の統合的探索に向けた連続腕バンディットの応用 / iot70_gp_rff_mab
monochromegane
2
190
スキマバイトサービスにおける現場起点でのデザインアプローチ
yoshioshingyouji
0
240
AI エージェントを活用した研究再現性の自動定量評価 / scisci2025
upura
1
160
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
3.7k
SNLP2025:Can Language Models Reason about Individualistic Human Values and Preferences?
yukizenimoto
0
190
大域マッチングコスト最小化とLiDAR-IMUタイトカップリングに基づく三次元地図生成 / GLIM @ Robotics symposia 2022
koide3
0
110
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
7
1.7k
Sat2City:3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion
satai
3
120
J-RAGBench: 日本語RAGにおける Generator評価ベンチマークの構築
koki_itai
0
700
Nullspace MPC
mizuhoaoki
1
180
とあるSREの博士「過程」 / A Certain SRE’s Ph.D. Journey
yuukit
11
4.4k
Featured
See All Featured
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
507
140k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
37
2.6k
It's Worth the Effort
3n
187
28k
Git: the NoSQL Database
bkeepers
PRO
431
66k
Navigating Team Friction
lara
190
15k
The Illustrated Children's Guide to Kubernetes
chrisshort
49
51k
GitHub's CSS Performance
jonrohan
1032
470k
Art, The Web, and Tiny UX
lynnandtonic
303
21k
The Language of Interfaces
destraynor
162
25k
Stop Working from a Prison Cell
hatefulcrawdad
271
21k
What's in a price? How to price your products and services
michaelherold
246
12k
Done Done
chrislema
185
16k
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.