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
90
Career Path Advice
nyghtowl
0
190
AI & Enterprise
nyghtowl
0
290
Artificial Intelligence
nyghtowl
2
760
Reinforcement Learning
nyghtowl
2
450
Machine Learning
nyghtowl
0
330
Machine Learning Resources
nyghtowl
0
87
What is AI? - Jerusalem
nyghtowl
0
250
Computer Vision Deep Learning with DL4J
nyghtowl
0
530
Other Decks in Technology
See All in Technology
Zero Data Loss Autonomous Recovery Service サービス概要
oracle4engineer
PRO
1
4.8k
レンジャーシステムズ | 会社紹介(採用ピッチ)
rssytems
0
300
「完全に理解したTalk」完全に理解した
segavvy
1
180
3年でバックエンドエンジニアが5倍に増えても破綻しなかったアーキテクチャ そして、これから / Software architecture that scales even with a 5x increase in backend engineers in 3 years
euglena1215
11
4k
なぜCodeceptJSを選んだか
goataka
0
190
終了の危機にあった15年続くWebサービスを全力で存続させる - phpcon2024
yositosi
27
24k
能動的ドメイン名ライフサイクル管理のすゝめ / Practice on Active Domain Name Lifecycle Management
nttcom
0
290
非機能品質を作り込むための実践アーキテクチャ
knih
5
1.7k
事業貢献を考えるための技術改善の目標設計と改善実績 / Targeted design of technical improvements to consider business contribution and improvement performance
oomatomo
0
170
DevFest 2024 Incheon / Songdo - Compose UI 조합 심화
wisemuji
0
190
クレカ・銀行連携機能における “状態”との向き合い方 / SmartBank Engineer LT Event
smartbank
2
110
大規模言語モデルとそのソフトウェア開発に向けた応用 (2024年版)
kazato
1
130
Featured
See All Featured
Art, The Web, and Tiny UX
lynnandtonic
298
20k
How To Stay Up To Date on Web Technology
chriscoyier
789
250k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
330
21k
GraphQLの誤解/rethinking-graphql
sonatard
67
10k
Imperfection Machines: The Place of Print at Facebook
scottboms
266
13k
Put a Button on it: Removing Barriers to Going Fast.
kastner
59
3.6k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
17
2.3k
Designing for humans not robots
tammielis
250
25k
Mobile First: as difficult as doing things right
swwweet
222
9k
Measuring & Analyzing Core Web Vitals
bluesmoon
5
180
Designing on Purpose - Digital PM Summit 2013
jponch
116
7k
How to Ace a Technical Interview
jacobian
276
23k
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