BERT を中心に解説した資料です.BERT に比べると,XLNet と RoBERTa の内容は詳細に追ってないです.
あと,自作の図は上から下ですが,引っ張ってきた図は下から上になっているので注意してください.
もし間違い等あったら修正するので,言ってください.
(特に,RoBERTa の英語を読み間違えがちょっと怖いです.言い訳すいません.)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
XLNet: Generalized Autoregressive Pretraining for Language Understanding
RoBERTa: A Robustly Optimized BERT Pretraining Approach
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement LearningPreferred Networks
Introduction of Deep Reinforcement Learning, which was presented at domestic NLP conference.
言語処理学会第24回年次大会(NLP2018) での講演資料です。
http://www.anlp.jp/nlp2018/#tutorial
BERT を中心に解説した資料です.BERT に比べると,XLNet と RoBERTa の内容は詳細に追ってないです.
あと,自作の図は上から下ですが,引っ張ってきた図は下から上になっているので注意してください.
もし間違い等あったら修正するので,言ってください.
(特に,RoBERTa の英語を読み間違えがちょっと怖いです.言い訳すいません.)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
XLNet: Generalized Autoregressive Pretraining for Language Understanding
RoBERTa: A Robustly Optimized BERT Pretraining Approach
ゼロから始める深層強化学習(NLP2018講演資料)/ Introduction of Deep Reinforcement LearningPreferred Networks
Introduction of Deep Reinforcement Learning, which was presented at domestic NLP conference.
言語処理学会第24回年次大会(NLP2018) での講演資料です。
http://www.anlp.jp/nlp2018/#tutorial
本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
안녕하세요. 이동민입니다. :)
2018. 8. 9일에 한국항공우주연구원에서 발표한 "Safe Reinforcement Learning" 발표 자료입니다.
목차는 다음과 같습니다.
1. Reinforcement Learning
2. Safe Reinforcement Learning
3. Optimization Criterion
4. Exploration Process
강화학습 계속 공부하면서 실제로 많은 분들이 쓸 수 있게 하려면 더 안전하고 빨라야한다는 생각이 들었습니다. 그래서 이에 관련하여 논문과 각종 자료들로 공부하여 발표하였습니다.
많은 분들께 도움이 되었으면 좋겠습니다. 감사합니다!
Show drafts
volume_up
Empowering the Data Analytics Ecosystem: A Laser Focus on Value
The data analytics ecosystem thrives when every component functions at its peak, unlocking the true potential of data. Here's a laser focus on key areas for an empowered ecosystem:
1. Democratize Access, Not Data:
Granular Access Controls: Provide users with self-service tools tailored to their specific needs, preventing data overload and misuse.
Data Catalogs: Implement robust data catalogs for easy discovery and understanding of available data sources.
2. Foster Collaboration with Clear Roles:
Data Mesh Architecture: Break down data silos by creating a distributed data ownership model with clear ownership and responsibilities.
Collaborative Workspaces: Utilize interactive platforms where data scientists, analysts, and domain experts can work seamlessly together.
3. Leverage Advanced Analytics Strategically:
AI-powered Automation: Automate repetitive tasks like data cleaning and feature engineering, freeing up data talent for higher-level analysis.
Right-Tool Selection: Strategically choose the most effective advanced analytics techniques (e.g., AI, ML) based on specific business problems.
4. Prioritize Data Quality with Automation:
Automated Data Validation: Implement automated data quality checks to identify and rectify errors at the source, minimizing downstream issues.
Data Lineage Tracking: Track the flow of data throughout the ecosystem, ensuring transparency and facilitating root cause analysis for errors.
5. Cultivate a Data-Driven Mindset:
Metrics-Driven Performance Management: Align KPIs and performance metrics with data-driven insights to ensure actionable decision making.
Data Storytelling Workshops: Equip stakeholders with the skills to translate complex data findings into compelling narratives that drive action.
Benefits of a Precise Ecosystem:
Sharpened Focus: Precise access and clear roles ensure everyone works with the most relevant data, maximizing efficiency.
Actionable Insights: Strategic analytics and automated quality checks lead to more reliable and actionable data insights.
Continuous Improvement: Data-driven performance management fosters a culture of learning and continuous improvement.
Sustainable Growth: Empowered by data, organizations can make informed decisions to drive sustainable growth and innovation.
By focusing on these precise actions, organizations can create an empowered data analytics ecosystem that delivers real value by driving data-driven decisions and maximizing the return on their data investment.
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...John Andrews
SlideShare Description for "Chatty Kathy - UNC Bootcamp Final Project Presentation"
Title: Chatty Kathy: Enhancing Physical Activity Among Older Adults
Description:
Discover how Chatty Kathy, an innovative project developed at the UNC Bootcamp, aims to tackle the challenge of low physical activity among older adults. Our AI-driven solution uses peer interaction to boost and sustain exercise levels, significantly improving health outcomes. This presentation covers our problem statement, the rationale behind Chatty Kathy, synthetic data and persona creation, model performance metrics, a visual demonstration of the project, and potential future developments. Join us for an insightful Q&A session to explore the potential of this groundbreaking project.
Project Team: Jay Requarth, Jana Avery, John Andrews, Dr. Dick Davis II, Nee Buntoum, Nam Yeongjin & Mat Nicholas
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Subhajit Sahu
Abstract — Levelwise PageRank is an alternative method of PageRank computation which decomposes the input graph into a directed acyclic block-graph of strongly connected components, and processes them in topological order, one level at a time. This enables calculation for ranks in a distributed fashion without per-iteration communication, unlike the standard method where all vertices are processed in each iteration. It however comes with a precondition of the absence of dead ends in the input graph. Here, the native non-distributed performance of Levelwise PageRank was compared against Monolithic PageRank on a CPU as well as a GPU. To ensure a fair comparison, Monolithic PageRank was also performed on a graph where vertices were split by components. Results indicate that Levelwise PageRank is about as fast as Monolithic PageRank on the CPU, but quite a bit slower on the GPU. Slowdown on the GPU is likely caused by a large submission of small workloads, and expected to be non-issue when the computation is performed on massive graphs.
7. 7y / - - - - - - :/ - -
b aL L s t w l u L
- - .- - C
ü D D
ü D
ü
ü f aho
ü
ü co
ü racs
ü cp s
ü c os
ü cS
ü cS D
ü it
ü c y
ü un f
ü c
ü e t
ü
ü c k a
ü c s
ü cL
ü c
ü c f d
S B
IL B
I
8. 8/ - - - - - - :/ - -
d ac L uo l n w
S - - .- - I I S
ü S S
ü S
ü
ü h c l
ü
ü i e l
ü tceu
ü i eriu
ü i e a u
ü i e S
ü i e S
ü b k
ü i e
ü wp h
ü i e
ü
ü
ü i e c
ü i e u l
ü i e
ü i e
ü i e h fs
y DD
C
B C
L
10. 10
w 9DDA : :2 ( ) 92D :776 6 6 2 D:7: :2 : D6 : 6 6 2 9: 6 62 : 66A 62 : 2:
v 02 9: 6 /62 : -66A /62 :
g av aM bh fc g
v aI_ av M . L . _I c
9DDA 2: 2 2: A : 1
va d e
i kspr la
n lijs mo
i at n l
e i w
c g
11. 11f 0::7 - 3 / : . 8 - 0 .: :0- 13 1 / 3 2 . 01 - 3- 8 1 / r gide m
o n
u
n
u
n
pmn
htr
ac
ld c b o n o n ks
h
12. 12g 0::7 - 3 / : . 8 - 0 .: :0- 13 1 / 3 2 . 01 - 3- 8 1 / s h ef n
p o
oo
no
k
ius r
a
bd
me d c p o p o lt
i
13. 13
loan_amnt annual_inc int_rate term emp_title emp_length home_ownership addr_state last_pymnt_d loan_condition
30000 100,000.00 22.35 36 months Supervisor 5 years MORTGAGE CA Jan-19 Good Loan
40000 45,000.00 16.14 60 months
Assistant to
the Treasurer
(Payroll)
< 1 year MORTGAGE OH Feb-19 Good Loan
8000 55,000.00 6.46 36 months Meat Cutter 10+ years MORTGAGE WA NaN Bad Loan
iy :: 4/ - / : 4/ . -4 . : 4
200
/ . 4 ( : u ) -/4 Cd np E cC bCegcC
o mw slL h ad mwcC x t cC k
6000 17,000.00 14.47 36 months NaN NaN MORTGAGE FL NaN
7500 50,000.00 12.73 36 months NaN NaN MORTGAGE IN Oct-18
30000 109,000.00 20.89 36 months President 8 years MORTGAGE TX Feb-19
D D
cC x D
33. GC E
33
Nc f Wc f c f W SaT W
Quora Insincere Questions
Classification
H
K
I
tp W SC W
t T
M
m e W r i C
/ 39 05 6S M
63
63
D
M
o
i
o
i
u
C yE y T
R 63
s W
p
TW C
Q M 63
b W
iMet Collection 2019 - FGVC6
1W 6 9 3 A 6A 7
W W Mnl
o M
63
W
264W
b
D
34. 34
/
ü l o t u
t u hu u R
ü K u ae D
R M
og pu / KS
og pu S
ü n K
M hu u
ü P S u y
M M
40. AI E
I H
DC
A
DC E
reMa M
DT i M
M re D DE CH AH
a rd M
I
A d p eL
B /
M
/M
A
M
T
e M
o
p eL B g VD
g e AH M
M
p e H L
L A B
AH re I R
DT M reM A
DT rdnee M
41. 41
a P a
h
ü
ü p h o A
ü
ü P A
ü x
ü iy ED
ü
ü A
ü i
ü x tn ED
ü l a
ü t a
ü i t
ü
ü h
ü A
ü x nrh s
ü a r
p
A
ü P x A p) ) (