The slides go through the implementation details of Google Deepmind's AlphaGo, a computer Go AI that defeated the European champion. The slides are targeted for beginners in the machine learning area.
Korean version (한국어 버젼): http://www.slideshare.net/ShaneSeungwhanMoon/ss-59226902
In this report, the key theoretical foundations and implementation details of AlphaGo, AlphaGo Zero, and Alpha Zero presented in the literature (mainly the two Nature papers) are introduced, followed a short discussion to imitation learning paradigm.
The slides go through the implementation details of Google Deepmind's AlphaGo, a computer Go AI that defeated the European champion. The slides are targeted for beginners in the machine learning area.
Korean version (한국어 버젼): http://www.slideshare.net/ShaneSeungwhanMoon/ss-59226902
In this report, the key theoretical foundations and implementation details of AlphaGo, AlphaGo Zero, and Alpha Zero presented in the literature (mainly the two Nature papers) are introduced, followed a short discussion to imitation learning paradigm.
AlphaZero: A General Reinforcement Learning Algorithm that Masters Chess, Sho...Joonhyung Lee
An introduction to DeepMind's newest board-game playing AI, AlphaZero.
I have improved significantly on my previous presentation in https://www.slideshare.net/ssuserc416e2/alphago-zero-mastering-the-game-of-go-without-human-knowledge, which had several errors (some rather glaring, such as the temperature equation for simulated annealing). Also, DeepMind released far more details in their new Science paper for AlphaZero.
One comment I would like to add is that the AlphaGo Zero used for comparison in this paper is a very weak version, not the final version. Thus, AlphaGo Zero is still SOTA for Go.
AlphaGo Zero: Mastering the Game of Go Without Human KnowledgeJoonhyung Lee
A brief but in-depth and highly understandable introduction to AlphaGo Zero, the successor to the world-famous AlphaGo.
Unlike its predecessor, which relied on a huge amount of human training data, AlphaGo Zero requires no human input in its training process.
Because of this, it is uninhibited by human prejudices and preconceptions, which allowed it to become the best go player, human or machine, in history.
This is the presentation that I gave concerning the subject in my first semester as a graduate subject. It was designed for those with a background in deep learning, but not reinforcement learning. It explains the core concepts necessary to understand AlphaGo to an interested audience.
Deliberately Planning and Acting for Angry Birds with Refinement MethodsRuofei Du
Authors: Ruofei Du, Zebao Gao, Zheng Xu; Advisors: Prof. Dana S. Nau and Dr. Vikas Shivashankar; This is a supplementary video for CMSC 722 AI Planning.
Check out papers, slides and more here: http://duruofei.com/Research/angrybirds
Angry Birds has been a popular game throughout the world since 2009. The goal of the game is to destroy all the pigs and as many obstacles as possible using a limited number of birds. Since the game environment is subject to change tremendously after each shot, a deterministic planning model is very likely to fail. In this paper, we integrate deliberately planning and acting for Angry Birds with refinement methods. Specifically, we design a refinement acting engine (RAE) based on ARP-interleave with Sequential Refinement Planning Engine (SeRPE). In addition, we implement greedy algorithm, Depth First Forward Search (DFFS) and $A^*$ algorithm to perform the actor's deliberation functions. Eventually, we evaluate our agent to solve the web version of Angry Birds in Chrome using the client-server platform provided by the IJCAI 2015 AI Birds Competition. In our experiments, we find out that our agent using SeRPE with $A^*$ algorithm greatly outperforms the agent using greedy algorithm or forward search without SeRPE. In this way, we prove the significance of refinement methods for planning in practice. Please see the supplementary video \url{https://youtu.be/u7XJ0g6d9po} for more results.
AI - A recap of the market
Machine Learning history and overview
Deep Learning explained in 2 slides
Deep Learning in Microsoft
Galaxy Classification in-depth
A demo!
A Development of Log-based Game AI using Deep LearningSuntae Kim
PyCon Korea 2018 발표자료입니다.
https://www.pycon.kr/2018/program/34
게임에서 AI는 빠질 수 없는 기능으로 그동안 다양한 장르와 플랫폼에서 사용되어 왔다.
특히 요즘 모바일 게임에서 자동 플레이 AI는 흔히 '노가다', '피로도'를 줄여주기 위한 매우 중요한 기능으로 자리잡고 있다. 하지만 지금까지의 자동 플레이 AI는 정해진 범위안에서 작동하는 FSM(Finite State Machine) 형태로 구현되다 보니 AI가 동작하는 경우의 수가 유한하고 한정적이라고 볼 수 있다. 때로는 이렇게 정해진 패턴의 AI가 유저들에게는 마치 로보트와 같은 느낌을 주기도 한다. 아무리 State를 추가하고 자연스럽게 구현해보려고 해도 어디까지 자연스럽게 해줘야 할 것인가에 대한 한계에 맞닥들이게 된다. 고려해야 할 경우의 수가 많기 때문이다.
하지만 이렇게 다양한 경우의 수를 로직으로 구현하지 않고 사용자가 플레이했던 데이터를 이용하여 학습시켜보면 어떨까? 이 호기심을 시작으로 LINE에서 자체 개발한 "리틀나이츠" 모바일 게임에 적용해보기로 했다. 게임 런칭 후 실제 사용자 플레이 로그를 수집하여 전처리하고 학습시켜서, 기획 의도에 맞게 유저가 Offline일 때 자신을 대신해서 플레이해 줄 수 있는 AI를 개발하였다. 이를 위해서 유저가 언제 어떤 카드를 선택했고 어디에 배치했는지, When, What, Where 3가지 상황에 대해서 학습시켰고 게임에 적용시켜 보았다.
단계별 과정을 간략하게 살펴보면, 먼저 로그 포멧을 게임 개발팀과 함께 정의했다. 두번째로 유저가 플레이했던 배틀 정보가 사전에 정의했던 로그 포맷 형태로 하둡에 쌓이게 했으며, 세번째로 Apache Spark을 이용하여 저장된 대용량 플레이 로그를 분산으로 전처리하여 데이터를 학습 가능한 형태로 가공하였다. 네번째로 AI 모델을 만들기 위한 뉴럴 네트워크를 설계하고, Python과 TensorFlow를 이용하여 데이터를 학습시켰다. 다섯번째로 학습에 반영되지 않는 순수한 테스트 데이터로 예측률을 구해본다. 이때 최적의 모델을 찾기 위해서 인내를 가지고 테스트하게 되는데, 먼저 하이퍼파라메터를 변경해보고 그래도 성능이 안나오면 뉴럴 네트워크와 데이터 전처리를 다양하게 변경해가며 테스트해 본다. 참고로 이러한 과정에 소비되는 Cost를 줄이고 싶다면 AutoML에 관심을 가져보아도 좋다. 여섯번째로 Python으로 개발된 AI 모델을 C# 기반의 유니티 환경에서 구동시키기 위해서 LineTensorFlow(가칭) 라이브러리를 개발해서 유니티 게임에 적용하였다.
발표 끝부분에서는 학습 지표를 공유하고, 알고리즘 기반의 AI와 딥러닝 기반의 AI에 대해서 플레이 비교 영상을 보고, 어떤 것이 딥러닝을 이용한 AI인지 맞춰보는 시간도 갖아본다. 이 발표에서는 로그 기반의 게임 AI가 개발되는 과정에서 파이썬이 어떻게 활용되었는지 살펴보고, 그 동안 겪었던 문제와 해결 방법에 대해서 공유하고자 한다.
A grand challenge of AI has fallen - a decade earlier than "experts" predicted. But should we care?
What made AlphaGo, the AI built by DeepMind, so unique?
Dive into AlphaGo's system of deep learning, evaluation, and search algorithms that combined to defeat the reigning Go world champion, and draw your own conclusions.
Tim Riser presented an analysis of "Mastering the Game of Go with Deep Neural Networks & Tree Search", a paper by Google DeepMind to the Boston/Cambridge chapter of Papers We Love, a computer science discussion group on June 28, 2016.
Slides for a short lecture (~1 hr) on the foundations of the Alpha Go model developed by Google. Intended for people with little technical background, but with basic familiarity with Deep Learning.
AlphaZero: A General Reinforcement Learning Algorithm that Masters Chess, Sho...Joonhyung Lee
An introduction to DeepMind's newest board-game playing AI, AlphaZero.
I have improved significantly on my previous presentation in https://www.slideshare.net/ssuserc416e2/alphago-zero-mastering-the-game-of-go-without-human-knowledge, which had several errors (some rather glaring, such as the temperature equation for simulated annealing). Also, DeepMind released far more details in their new Science paper for AlphaZero.
One comment I would like to add is that the AlphaGo Zero used for comparison in this paper is a very weak version, not the final version. Thus, AlphaGo Zero is still SOTA for Go.
AlphaGo Zero: Mastering the Game of Go Without Human KnowledgeJoonhyung Lee
A brief but in-depth and highly understandable introduction to AlphaGo Zero, the successor to the world-famous AlphaGo.
Unlike its predecessor, which relied on a huge amount of human training data, AlphaGo Zero requires no human input in its training process.
Because of this, it is uninhibited by human prejudices and preconceptions, which allowed it to become the best go player, human or machine, in history.
This is the presentation that I gave concerning the subject in my first semester as a graduate subject. It was designed for those with a background in deep learning, but not reinforcement learning. It explains the core concepts necessary to understand AlphaGo to an interested audience.
Deliberately Planning and Acting for Angry Birds with Refinement MethodsRuofei Du
Authors: Ruofei Du, Zebao Gao, Zheng Xu; Advisors: Prof. Dana S. Nau and Dr. Vikas Shivashankar; This is a supplementary video for CMSC 722 AI Planning.
Check out papers, slides and more here: http://duruofei.com/Research/angrybirds
Angry Birds has been a popular game throughout the world since 2009. The goal of the game is to destroy all the pigs and as many obstacles as possible using a limited number of birds. Since the game environment is subject to change tremendously after each shot, a deterministic planning model is very likely to fail. In this paper, we integrate deliberately planning and acting for Angry Birds with refinement methods. Specifically, we design a refinement acting engine (RAE) based on ARP-interleave with Sequential Refinement Planning Engine (SeRPE). In addition, we implement greedy algorithm, Depth First Forward Search (DFFS) and $A^*$ algorithm to perform the actor's deliberation functions. Eventually, we evaluate our agent to solve the web version of Angry Birds in Chrome using the client-server platform provided by the IJCAI 2015 AI Birds Competition. In our experiments, we find out that our agent using SeRPE with $A^*$ algorithm greatly outperforms the agent using greedy algorithm or forward search without SeRPE. In this way, we prove the significance of refinement methods for planning in practice. Please see the supplementary video \url{https://youtu.be/u7XJ0g6d9po} for more results.
AI - A recap of the market
Machine Learning history and overview
Deep Learning explained in 2 slides
Deep Learning in Microsoft
Galaxy Classification in-depth
A demo!
A Development of Log-based Game AI using Deep LearningSuntae Kim
PyCon Korea 2018 발표자료입니다.
https://www.pycon.kr/2018/program/34
게임에서 AI는 빠질 수 없는 기능으로 그동안 다양한 장르와 플랫폼에서 사용되어 왔다.
특히 요즘 모바일 게임에서 자동 플레이 AI는 흔히 '노가다', '피로도'를 줄여주기 위한 매우 중요한 기능으로 자리잡고 있다. 하지만 지금까지의 자동 플레이 AI는 정해진 범위안에서 작동하는 FSM(Finite State Machine) 형태로 구현되다 보니 AI가 동작하는 경우의 수가 유한하고 한정적이라고 볼 수 있다. 때로는 이렇게 정해진 패턴의 AI가 유저들에게는 마치 로보트와 같은 느낌을 주기도 한다. 아무리 State를 추가하고 자연스럽게 구현해보려고 해도 어디까지 자연스럽게 해줘야 할 것인가에 대한 한계에 맞닥들이게 된다. 고려해야 할 경우의 수가 많기 때문이다.
하지만 이렇게 다양한 경우의 수를 로직으로 구현하지 않고 사용자가 플레이했던 데이터를 이용하여 학습시켜보면 어떨까? 이 호기심을 시작으로 LINE에서 자체 개발한 "리틀나이츠" 모바일 게임에 적용해보기로 했다. 게임 런칭 후 실제 사용자 플레이 로그를 수집하여 전처리하고 학습시켜서, 기획 의도에 맞게 유저가 Offline일 때 자신을 대신해서 플레이해 줄 수 있는 AI를 개발하였다. 이를 위해서 유저가 언제 어떤 카드를 선택했고 어디에 배치했는지, When, What, Where 3가지 상황에 대해서 학습시켰고 게임에 적용시켜 보았다.
단계별 과정을 간략하게 살펴보면, 먼저 로그 포멧을 게임 개발팀과 함께 정의했다. 두번째로 유저가 플레이했던 배틀 정보가 사전에 정의했던 로그 포맷 형태로 하둡에 쌓이게 했으며, 세번째로 Apache Spark을 이용하여 저장된 대용량 플레이 로그를 분산으로 전처리하여 데이터를 학습 가능한 형태로 가공하였다. 네번째로 AI 모델을 만들기 위한 뉴럴 네트워크를 설계하고, Python과 TensorFlow를 이용하여 데이터를 학습시켰다. 다섯번째로 학습에 반영되지 않는 순수한 테스트 데이터로 예측률을 구해본다. 이때 최적의 모델을 찾기 위해서 인내를 가지고 테스트하게 되는데, 먼저 하이퍼파라메터를 변경해보고 그래도 성능이 안나오면 뉴럴 네트워크와 데이터 전처리를 다양하게 변경해가며 테스트해 본다. 참고로 이러한 과정에 소비되는 Cost를 줄이고 싶다면 AutoML에 관심을 가져보아도 좋다. 여섯번째로 Python으로 개발된 AI 모델을 C# 기반의 유니티 환경에서 구동시키기 위해서 LineTensorFlow(가칭) 라이브러리를 개발해서 유니티 게임에 적용하였다.
발표 끝부분에서는 학습 지표를 공유하고, 알고리즘 기반의 AI와 딥러닝 기반의 AI에 대해서 플레이 비교 영상을 보고, 어떤 것이 딥러닝을 이용한 AI인지 맞춰보는 시간도 갖아본다. 이 발표에서는 로그 기반의 게임 AI가 개발되는 과정에서 파이썬이 어떻게 활용되었는지 살펴보고, 그 동안 겪었던 문제와 해결 방법에 대해서 공유하고자 한다.
A grand challenge of AI has fallen - a decade earlier than "experts" predicted. But should we care?
What made AlphaGo, the AI built by DeepMind, so unique?
Dive into AlphaGo's system of deep learning, evaluation, and search algorithms that combined to defeat the reigning Go world champion, and draw your own conclusions.
Tim Riser presented an analysis of "Mastering the Game of Go with Deep Neural Networks & Tree Search", a paper by Google DeepMind to the Boston/Cambridge chapter of Papers We Love, a computer science discussion group on June 28, 2016.
Slides for a short lecture (~1 hr) on the foundations of the Alpha Go model developed by Google. Intended for people with little technical background, but with basic familiarity with Deep Learning.
Ropossum is a framework that lets you play the beloved Cut The Rope game as much as you want and the levels will keep coming. You can design your own levels, check your designed levels for playability at real time, ask it to complete your unfinished designs according to your own preferences, or even suggest endless playable design variations according to your initial level design.
La question de la durabilité des technologies de calcul et de télécommunicationAlexandre Monnin
Intervention de José Halloy (Professeur de Physique à l'Université Paris Diderot), dans le Cadre du Café-In du jeudi 11 mai 2017, dans les locaux du centre de recherche d'Inria Sophia Antipolis - Méditerranée.
MongoDB.local Seattle 2019: Tips & Tricks for Avoiding Common Query PitfallsMongoDB
Query performance can either be a constant headache or the unsung hero of an application. MongoDB provides extremely powerful querying capabilities when used properly. As a member of the support team I will share common mistakes observed as well as tips and tricks to avoiding them.
Safalta Digital marketing institute in Noida, provide complete applications that encompass a huge range of virtual advertising and marketing additives, which includes search engine optimization, virtual communication advertising, pay-per-click on marketing, content material advertising, internet analytics, and greater. These university courses are designed for students who possess a comprehensive understanding of virtual marketing strategies and attributes.Safalta Digital Marketing Institute in Noida is a first choice for young individuals or students who are looking to start their careers in the field of digital advertising. The institute gives specialized courses designed and certification.
for beginners, providing thorough training in areas such as SEO, digital communication marketing, and PPC training in Noida. After finishing the program, students receive the certifications recognised by top different universitie, setting a strong foundation for a successful career in digital marketing.
June 3, 2024 Anti-Semitism Letter Sent to MIT President Kornbluth and MIT Cor...Levi Shapiro
Letter from the Congress of the United States regarding Anti-Semitism sent June 3rd to MIT President Sally Kornbluth, MIT Corp Chair, Mark Gorenberg
Dear Dr. Kornbluth and Mr. Gorenberg,
The US House of Representatives is deeply concerned by ongoing and pervasive acts of antisemitic
harassment and intimidation at the Massachusetts Institute of Technology (MIT). Failing to act decisively to ensure a safe learning environment for all students would be a grave dereliction of your responsibilities as President of MIT and Chair of the MIT Corporation.
This Congress will not stand idly by and allow an environment hostile to Jewish students to persist. The House believes that your institution is in violation of Title VI of the Civil Rights Act, and the inability or
unwillingness to rectify this violation through action requires accountability.
Postsecondary education is a unique opportunity for students to learn and have their ideas and beliefs challenged. However, universities receiving hundreds of millions of federal funds annually have denied
students that opportunity and have been hijacked to become venues for the promotion of terrorism, antisemitic harassment and intimidation, unlawful encampments, and in some cases, assaults and riots.
The House of Representatives will not countenance the use of federal funds to indoctrinate students into hateful, antisemitic, anti-American supporters of terrorism. Investigations into campus antisemitism by the Committee on Education and the Workforce and the Committee on Ways and Means have been expanded into a Congress-wide probe across all relevant jurisdictions to address this national crisis. The undersigned Committees will conduct oversight into the use of federal funds at MIT and its learning environment under authorities granted to each Committee.
• The Committee on Education and the Workforce has been investigating your institution since December 7, 2023. The Committee has broad jurisdiction over postsecondary education, including its compliance with Title VI of the Civil Rights Act, campus safety concerns over disruptions to the learning environment, and the awarding of federal student aid under the Higher Education Act.
• The Committee on Oversight and Accountability is investigating the sources of funding and other support flowing to groups espousing pro-Hamas propaganda and engaged in antisemitic harassment and intimidation of students. The Committee on Oversight and Accountability is the principal oversight committee of the US House of Representatives and has broad authority to investigate “any matter” at “any time” under House Rule X.
• The Committee on Ways and Means has been investigating several universities since November 15, 2023, when the Committee held a hearing entitled From Ivory Towers to Dark Corners: Investigating the Nexus Between Antisemitism, Tax-Exempt Universities, and Terror Financing. The Committee followed the hearing with letters to those institutions on January 10, 202
Francesca Gottschalk - How can education support child empowerment.pptxEduSkills OECD
Francesca Gottschalk from the OECD’s Centre for Educational Research and Innovation presents at the Ask an Expert Webinar: How can education support child empowerment?
A workshop hosted by the South African Journal of Science aimed at postgraduate students and early career researchers with little or no experience in writing and publishing journal articles.
Exploiting Artificial Intelligence for Empowering Researchers and Faculty, In...Dr. Vinod Kumar Kanvaria
Exploiting Artificial Intelligence for Empowering Researchers and Faculty,
International FDP on Fundamentals of Research in Social Sciences
at Integral University, Lucknow, 06.06.2024
By Dr. Vinod Kumar Kanvaria
Operation “Blue Star” is the only event in the history of Independent India where the state went into war with its own people. Even after about 40 years it is not clear if it was culmination of states anger over people of the region, a political game of power or start of dictatorial chapter in the democratic setup.
The people of Punjab felt alienated from main stream due to denial of their just demands during a long democratic struggle since independence. As it happen all over the word, it led to militant struggle with great loss of lives of military, police and civilian personnel. Killing of Indira Gandhi and massacre of innocent Sikhs in Delhi and other India cities was also associated with this movement.
How to Make a Field invisible in Odoo 17Celine George
It is possible to hide or invisible some fields in odoo. Commonly using “invisible” attribute in the field definition to invisible the fields. This slide will show how to make a field invisible in odoo 17.
Synthetic Fiber Construction in lab .pptxPavel ( NSTU)
Synthetic fiber production is a fascinating and complex field that blends chemistry, engineering, and environmental science. By understanding these aspects, students can gain a comprehensive view of synthetic fiber production, its impact on society and the environment, and the potential for future innovations. Synthetic fibers play a crucial role in modern society, impacting various aspects of daily life, industry, and the environment. ynthetic fibers are integral to modern life, offering a range of benefits from cost-effectiveness and versatility to innovative applications and performance characteristics. While they pose environmental challenges, ongoing research and development aim to create more sustainable and eco-friendly alternatives. Understanding the importance of synthetic fibers helps in appreciating their role in the economy, industry, and daily life, while also emphasizing the need for sustainable practices and innovation.
Biological screening of herbal drugs: Introduction and Need for
Phyto-Pharmacological Screening, New Strategies for evaluating
Natural Products, In vitro evaluation techniques for Antioxidants, Antimicrobial and Anticancer drugs. In vivo evaluation techniques
for Anti-inflammatory, Antiulcer, Anticancer, Wound healing, Antidiabetic, Hepatoprotective, Cardio protective, Diuretics and
Antifertility, Toxicity studies as per OECD guidelines
Natural birth techniques - Mrs.Akanksha Trivedi Rama University
Chakrabarti alpha go analysis
1. AlphaGo
Analysis
from
Deep
Learning
Perspec6ve
Chayan
Chakrabar6
July
11,
2016
Pleasanton,
CA
2. Mastering
the
game
of
GO
• DeepMind
problem
domain
• Deep
learning
and
reinforcement
learning
concepts
• Design
of
AlphaGo
• Execu6on
3. GO:
perfect
informa6on
game
All
possible
GO
boards
=
250150
>
Number
of
atoms
in
the
universe
4. Reduce
search
space
• Reduce
breadth
– Not
all
moves
are
equally
likely
– Some
moves
are
bePer
– Leverage
moves
made
by
expert
players
• Reduce
depth
– Evaluate
strength
of
board
(likelihood
of
winning)
– Collapse
symmetrical
or
similar
boards
– Simulate
the
games
17. Two
kinds
of
policies
● used a large database of online expert games
● learned two versions of the neural network
○ a fast network P for use in evaluation
○ an accurate network P for use in selection
Step 1: learn to predict human moves
CS63 topic
neural networks
week 7, 14?
19. Reduce
depth
by
board
evalua6on
Updated$Model
ver 1,000,000
Board$Position
Training:
Value$
Predictio
Model
(Regressio
Evaluation
Updated$Model
W
Value$
Prediction$
Adds$a reg
Predicts$v
Close$to$1
Close$to$0
Win$/$Loss
e$
Adds$a regression$layer$to$the$model
Predicts$values$between$0~1
Close$to$1:$a$good$board$position
Close$to$0:$a$bad$board$position
aluation
Updated$Model
ver 1,000,000
Training:
Win$/$Loss
Win
(0~1)
Value$
Prediction$
Model
(Regression)
Adds$a regression$layer$to$the$model
Predicts$values$between$0~1
Close$to$1:$a$good$board$position
Close$to$0:$a$bad$board$position
20. Value
follows
from
policy
Step 3: learn a board evaluation network, V
● use random samples from the self-play database
● prediction target: probability that black wins from a
given board
21. PuWng
it
all
together
Looking*ahead*(w/*Monte*Carlo*Search*Tree)
Action$Candidates$Reduction
(Policy$Network)
Board$Evaluation
(Value$Network)
(Rollout):$Faster$version$of$estimating$p(a|s)
! uses shallow$networks$(3$ms ! 2µs)
27. Apply
trained
networks
to
tasks
with
different
loss
func6on
Takeaways
Use+the+networks+trained+for+a+certain+task+(with+different+loss+objectives)+for+several+other+ta
28. Single
most
important
takeaway
• Feature
abstrac6on
is
the
key
component
of
any
machine
learning
algorithm
• Convolu6onal
neural
networks
are
great
at
automated
feature
abstrac6on
29. Reference
Silver
et.
al.
Mastering
the
Game
of
Go
with
Deep
Neural
Networks
and
Tree
Search.
Nature.
529,
484–489.
January
2016.
30. About
the
speaker
Chayan
Chakrabar6
hPps://www.linkedin.com/in/chayanchakrabar6