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
Deep Learning and Natural Language Processing w...
Search
Melanie Warrick
June 17, 2016
Technology
1
450
Deep Learning and Natural Language Processing with Spark - Berlin
Melanie Warrick
June 17, 2016
Tweet
Share
More Decks by Melanie Warrick
See All by Melanie Warrick
PyCon.ru RL Talk Resources
nyghtowl
0
93
Career Path Advice
nyghtowl
0
200
AI & Enterprise
nyghtowl
0
300
Artificial Intelligence
nyghtowl
2
760
Reinforcement Learning
nyghtowl
2
460
Machine Learning
nyghtowl
0
330
Machine Learning Resources
nyghtowl
0
88
What is AI? - Jerusalem
nyghtowl
0
250
Computer Vision Deep Learning with DL4J
nyghtowl
0
540
Other Decks in Technology
See All in Technology
ユーザーストーリーマッピングから始めるアジャイルチームと並走するQA / Starting QA with User Story Mapping
katawara
0
170
MC906491 を見据えた Microsoft Entra Connect アップグレード対応
tamaiyutaro
1
520
プロセス改善による品質向上事例
tomasagi
2
2.2k
開発スピードは上がっている…品質はどうする? スピードと品質を両立させるためのプロダクト開発の進め方とは #DevSumi #DevSumiB / Agile And Quality
nihonbuson
2
2.4k
次世代KYC活動報告 / 20250219-BizDay17-KYC-nextgen
oidfj
0
150
人はなぜISUCONに夢中になるのか
kakehashi
PRO
6
1.5k
SA Night #2 FinatextのSA思想/SA Night #2 Finatext session
satoshiimai
1
130
OpenID Connect for Identity Assurance の概要と翻訳版のご紹介 / 20250219-BizDay17-OIDC4IDA-Intro
oidfj
0
160
リアルタイム分析データベースで実現する SQLベースのオブザーバビリティ
mikimatsumoto
0
1.2k
目の前の仕事と向き合うことで成長できる - 仕事とスキルを広げる / Every little bit counts
soudai
24
6.6k
Tech Blogを書きやすい環境づくり
lycorptech_jp
PRO
1
230
バックエンドエンジニアのためのフロントエンド入門 #devsumiC
panda_program
16
7k
Featured
See All Featured
Building Applications with DynamoDB
mza
93
6.2k
A designer walks into a library…
pauljervisheath
205
24k
Fashionably flexible responsive web design (full day workshop)
malarkey
406
66k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
29
1k
Statistics for Hackers
jakevdp
797
220k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
174
51k
Facilitating Awesome Meetings
lara
51
6.2k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
9
430
It's Worth the Effort
3n
184
28k
Mobile First: as difficult as doing things right
swwweet
223
9.3k
Bash Introduction
62gerente
610
210k
Building Flexible Design Systems
yeseniaperezcruz
328
38k
Transcript
Deep Learning and Natural Language Processing with Spark Melanie Warrick
| Skymind | @nyghtowl Andy Petrella | Data Fellas | @noootsab
@nyghtowl Machine Learning
None
@nyghtowl
@nyghtowl
Natural Language Processing @nyghtowl • Question Answer • Image Captioning
• Topic Modeling/Sentiment Analysis • Language | Machine Translation • Text Generation NLP is hard
@nyghtowl Artificial Neural Nets Output | y Hidden Loss Function
Output k j X M kj W y Run until error stops improving = converge Input | X
@nyghtowl Recurrent Neural Net
@nyghtowl Long short-term Memory (LSTM)
@nyghtowl Sequence to Sequence
@nyghtowl Example: Word2Vec Word embeddings represent context King – Man
+ Woman ~ Queen
@nyghtowl Example: Image Captioning
@nyghtowl Sequence to Sequence
@nyghtowl Sentiment Analysis Reviews “Best part of the movie is
the end credits” “It should have been a great movie…” Sentiment
@nyghtowl Hadoop Spark AWS Skymind ND4J DeepLearning4J Native & JavaCPP
& OpenMP & Cuda 7.5 Canova Data Neural Nets Linear Algebra LIBND4J C Backend
@nyghtowl Data Fellas - Spark-Notebook only Scala based notebook that
is - scalable and enables interactive work on Spark, Akka, Cassandra, & Kafka - plotting interactive plots in any Scala type - Data Fellas enables data-driven business, bringing productivity to data science in enterprise
@nyghtowl Cluster Juju bundle including: • DL4J • Mesos •
Spark • Spark Notebook
@nyghtowl Blog Making deep learning accessible on Openstack
@nyghtowl Research References RNNs • DL4J Overview: ◦ RNN &
LSTM Overview: http://deeplearning4j.org/recurrentnetwork ◦ Using RNNs: http://deeplearning4j.org/usingrnns.html • Karpathy: https://karpathy.github.io/2015/05/21/rnn-effectiveness/ • Intro: http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/ Github Repos • Spark Notebook: https://github.com/andypetrella/spark-notebook • DL4J Examples: https://github.com/deeplearning4j/dl4j-0.4-examples • DL4J Spark Examples: https://github.com/deeplearning4j/dl4j-spark-cdh5-examples General ML Projects (referenced in presentation) • AlphaGo: http://i.dailymail.co.uk/i/pix/2016/03/09/09/320583D500000578-3483569- Google_has_confirmed_its_AlphaGo_computer_has_taken_the_first_vi-a-11_1457516282972.jpg • Switzerland SAR: http://www.forensicmag.com/article/2016/02/autonomous-drones-fly-search-and-rescue-operations • VIV: http://www.dailytech.com/ExSiri+CEO+Poaches+Apple+to+Create+Viv+The+Global+Brain/article36387.htm
@nyghtowl Image References • http://www.dailytech. com/ExSiri+CEO+Poaches+Apple+to+Create+Viv+The+Global+Brain/article36387.htm • http://3.bp.blogspot.com/- mMPT3tgVWaQ/U5qVs64HbRI/AAAAAAAAJCM/lEE4OiJmRSY/s1600/thumb-down-smiley.png •
http://4.bp.blogspot.com/-pUoO5oOuzOc/VcomU6qKT4I/AAAAAAAAAsg/TonkgL1iEjE/s1600/Screen% 2BShot%2B2015-08-11%2Bat%2B9.43.21%2BAM.png • http://www.ucreative.com/inspiration/interesting-patterns-and-fractals-from-nature/ • http://i.telegraph.co.uk/multimedia/archive/02122/WILLIAM-SHAKESPEAR_2122089b.jpg • https://karpathy.github.io/2015/05/21/rnn-effectiveness/ • https://pbs.twimg.com/media/CJm9HmfVEAEXU0c.jpg:large • http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/ • http://i.dailymail.co.uk/i/pix/2016/03/09/09/320583D500000578-3483569- Google_has_confirmed_its_AlphaGo_computer_has_taken_the_first_vi-a-11_1457516282972.jpg • http://www.forensicmag.com/article/2016/02/autonomous-drones-fly-search-and-rescue-operations • Susan Eraly
@nyghtowl Deep Learning and Natural Language Processing with Spark Andy
Petrella | Data Fellas | @noootsab Melanie Warrick | Skymind | @nyghtowl