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
99
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
36
NLP for poetry generation and analysis
manexagirrezabal
0
78
Institut seminar 2020
manexagirrezabal
0
39
Automatic Scansion of Poetry (KU)
manexagirrezabal
0
660
RANLP talk
manexagirrezabal
0
77
Defense (Final version)
manexagirrezabal
0
74
Poesiaren eskantsio automatikoa: Bi hizkuntzen azterketa
manexagirrezabal
0
78
CodeFEST literature presentation
manexagirrezabal
0
63
Ongoing work (in mid 2016)
manexagirrezabal
0
27
Other Decks in Research
See All in Research
Off-Policy Evaluation and Learning for Matching Markets
yudai00
0
100
AIスパコン「さくらONE」の オブザーバビリティ / Observability for AI Supercomputer SAKURAONE
yuukit
2
1.3k
AIスーパーコンピュータにおけるLLM学習処理性能の計測と可観測性 / AI Supercomputer LLM Benchmarking and Observability
yuukit
1
730
【NICOGRAPH2025】Photographic Conviviality: ボディペイント・ワークショップによる 同時的かつ共生的な写真体験
toremolo72
0
190
Agentic AI フレームワーク戦略白書 (2025年度版)
mickey_kubo
1
130
"主観で終わらせない"定性データ活用 ― プロダクトディスカバリーを加速させるインサイトマネジメント / Utilizing qualitative data that "doesn't end with subjectivity" - Insight management that accelerates product discovery
kaminashi
16
22k
ペットのかわいい瞬間を撮影する オートシャッターAIアプリへの スマートラベリングの適用
mssmkmr
0
370
ローテーション別のサイドアウト戦略 ~なぜあのローテは回らないのか?~
vball_panda
0
300
YOLO26_ Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
satai
3
100
2026年1月の生成AI領域の重要リリース&トピック解説
kajikent
0
810
視覚から身体性を持つAIへ: 巧緻な動作の3次元理解
tkhkaeio
1
210
空間音響処理における物理法則に基づく機械学習
skoyamalab
0
240
Featured
See All Featured
Practical Orchestrator
shlominoach
191
11k
Crafting Experiences
bethany
1
81
4 Signs Your Business is Dying
shpigford
187
22k
30 Presentation Tips
portentint
PRO
1
250
Ecommerce SEO: The Keys for Success Now & Beyond - #SERPConf2024
aleyda
1
1.8k
Large-scale JavaScript Application Architecture
addyosmani
515
110k
Introduction to Domain-Driven Design and Collaborative software design
baasie
1
630
State of Search Keynote: SEO is Dead Long Live SEO
ryanjones
0
150
Principles of Awesome APIs and How to Build Them.
keavy
128
17k
Building a Scalable Design System with Sketch
lauravandoore
463
34k
The Illustrated Guide to Node.js - THAT Conference 2024
reverentgeek
1
300
Avoiding the “Bad Training, Faster” Trap in the Age of AI
tmiket
0
98
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.