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
90
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
71
Institut seminar 2020
manexagirrezabal
0
34
Automatic Scansion of Poetry (KU)
manexagirrezabal
0
590
RANLP talk
manexagirrezabal
0
73
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
Adaptive Experimental Design for Efficient Average Treatment Effect Estimation and Treatment Choice
masakat0
0
110
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
940
利用シーンを意識した推薦システム〜SpotifyとAmazonの事例から〜
kuri8ive
1
250
20250605_新交通システム推進議連_熊本都市圏「車1割削減、渋滞半減、公共交通2倍」から考える地方都市交通政策
trafficbrain
0
770
CVPR2025論文紹介:Unboxed
murakawatakuya
0
150
A scalable, annual aboveground biomass product for monitoring carbon impacts of ecosystem restoration projects
satai
4
230
数理最適化に基づく制御
mickey_kubo
6
730
SSII2025 [TS2] リモートセンシング画像処理の最前線
ssii
PRO
7
3.1k
AIスパコン「さくらONE」のLLM学習ベンチマークによる性能評価 / SAKURAONE LLM Training Benchmarking
yuukit
0
320
Towards a More Efficient Reasoning LLM: AIMO2 Solution Summary and Introduction to Fast-Math Models
analokmaus
2
790
【緊急警告】日本の未来設計図 ~沈没か、再生か。国民と断行するラストチャンス~
yuutakasan
0
150
SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images
satai
3
170
Featured
See All Featured
It's Worth the Effort
3n
187
28k
Designing Experiences People Love
moore
142
24k
Balancing Empowerment & Direction
lara
3
620
The Language of Interfaces
destraynor
161
25k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
188
55k
Raft: Consensus for Rubyists
vanstee
140
7.1k
The Art of Programming - Codeland 2020
erikaheidi
56
13k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.1k
The Power of CSS Pseudo Elements
geoffreycrofte
77
6k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
30
9.7k
Building Adaptive Systems
keathley
43
2.7k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
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.