Home
Explore
Submit Search
Upload
Login
Signup
Advertisement
Check these out next
GAN for business value @ Data Science Milan
Alex Honchar
The world runs on AI - Tony Krijnen (Microsoft) at GoDataFest 2019
GoDataDriven
Session 2 - Emerging Technologies in your Mobile Practice
Xamarin
Dev Secops Software Supply Chain
Cameron Townshend
Artificial Intelligence in testing - A STeP-IN Evening Talk Session Speech by...
Kalilur Rahman
Rise of the Machines - AI in the Agile World
Aidan Casey
Data Science for Beginner by Chetan Khatri and Deptt. of Computer Science, Ka...
Chetan Khatri
Resume
pranavmicro7
1
of
51
Top clipped slide
Beating us at our own Games
Sep. 22, 2017
•
0 likes
1 likes
×
Be the first to like this
Show More
•
89 views
views
×
Total views
0
On Slideshare
0
From embeds
0
Number of embeds
0
Download Now
Download to read offline
Report
Technology
Talk given at KPMG innovation workshop held on 2017-09-22
Melvin Zhang
Follow
Programmer at Cosmiqo · Magarena
Advertisement
Advertisement
Advertisement
Recommended
Being Practical About Artificial Intelligence (Forbes U30 Summit 2016)
Tarun Gangwani
243 views
•
26 slides
IEEE big data 2015
Dippy Aggarwal
361 views
•
16 slides
Chimpanzee
The Lower School
279 views
•
6 slides
Make it Fixable (CppCon 2018)
Patricia Aas
263 views
•
46 slides
Xamarin essentials un API cross-platform para gobernarlos a todos
Luis Beltran
153 views
•
28 slides
AI for IA's: Machine Learning Demystified at IA Summit 2017 - IAS17
Carol Smith
6K views
•
69 slides
More Related Content
Similar to Beating us at our own Games
(20)
GAN for business value @ Data Science Milan
Alex Honchar
•
125 views
The world runs on AI - Tony Krijnen (Microsoft) at GoDataFest 2019
GoDataDriven
•
620 views
Session 2 - Emerging Technologies in your Mobile Practice
Xamarin
•
306 views
Dev Secops Software Supply Chain
Cameron Townshend
•
110 views
Artificial Intelligence in testing - A STeP-IN Evening Talk Session Speech by...
Kalilur Rahman
•
764 views
Rise of the Machines - AI in the Agile World
Aidan Casey
•
352 views
Data Science for Beginner by Chetan Khatri and Deptt. of Computer Science, Ka...
Chetan Khatri
•
196 views
Resume
pranavmicro7
•
60 views
Rockstar datascientist
Juan Camilo Vasquez
•
386 views
Social Connections 14 - You Get What You Give
panagenda
•
575 views
China Digital Economy
Melanie Swan
•
892 views
Mining Software Repositories: Using Humans to Better Software
Marat Akhin
•
786 views
Artificial Intelligence Future
Prem Mohan
•
285 views
CWIN17 san francisco-ai implementation-pub
Capgemini
•
726 views
Fraud Detection is Easily Fooled
Dr. Augustine Fou - Independent Ad Fraud Researcher
•
2.2K views
Ai lastyearprogress-atlas-2019-04-26-190428120255
Aravindharamanan S
•
41 views
AI - Last Year Progress (2018-2019)
Grigory Sapunov
•
4.6K views
Ai ml-demystified-mwux2017-final-171016011705
Sindisiwe Mandlenkosi
•
40 views
Ml7
poovarasu maniandan
•
62 views
Ai ml-demystified-mwux2017-final-171016011705
dandh dandh
•
46 views
More from Melvin Zhang
(19)
How Alan Turing accidentally invented Software
Melvin Zhang
•
151 views
Solving the TSP for warehouses
Melvin Zhang
•
86 views
Optimize all the things with MiniZinc
Melvin Zhang
•
270 views
AMKSS Career Conference 2018: Software Engineering
Melvin Zhang
•
105 views
Getting started with open source game playing AIs
Melvin Zhang
•
195 views
Programs that Play better than Us
Melvin Zhang
•
246 views
Building a Turing Machine emulator to explore Turing's great ideas
Melvin Zhang
•
311 views
Lessons from Developing an AI to Play Magic: The Gathering
Melvin Zhang
•
489 views
Functional programming from first principles
Melvin Zhang
•
992 views
Binary Lambda Calculus and Combinatory Logic
Melvin Zhang
•
1.2K views
AMKSS Career Conference 2015: Programming
Melvin Zhang
•
378 views
Building a state of the art AI to play Magic: The Gathering
Melvin Zhang
•
4.2K views
Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search
Melvin Zhang
•
1.1K views
Quest for the optimal algorithm
Melvin Zhang
•
736 views
Playing Games by Throwing Dice
Melvin Zhang
•
351 views
Becoming a better problem solver: a CS perspective
Melvin Zhang
•
707 views
Ortholog assignment
Melvin Zhang
•
2.4K views
Building pipelines with Make
Melvin Zhang
•
281 views
Opportunities in STEM
Melvin Zhang
•
198 views
Advertisement
Recently uploaded
(20)
Divide_and_Contrast__Source_free_Domain_Adaptation_via_Adaptive_Contrastive_L...
Huang Po Chun
•
0 views
Ch 2.pdf
MuhammadAsif1069
•
0 views
Real-Time Text and WebRTC @ Kamailio World 2023
Lorenzo Miniero
•
0 views
TenT-Day03.pptx
JohanMyburgh15
•
0 views
Fast and Stable Ukraine Dedicated Server by Ukraine Server Hosting
UkraineServerHosting
•
0 views
TenT-Day06.pptx
JohanMyburgh15
•
0 views
AWS_FSI_Migrations_Webinar_PPT.pdf
Abhinav Gupta
•
0 views
2008-03-04 - Geoprocessing with ArcGIS.pdf
ssuseref75f1
•
0 views
4.1 Modeling Data Relationships.pdf
Felipelipilef2nd
•
0 views
Ch 3.pdf
MuhammadAsif1069
•
0 views
Vin secure solutions PPT (1).pdf
vin secure solutions
•
0 views
DNS Security Strategy
Andreas Taudte
•
0 views
TenT-Day08.pptx
JohanMyburgh15
•
0 views
Copy of Blue and Red, Minimal Gradient FinTech Pitch Deck.pptx
Shashank275320
•
0 views
TenT-Day04.pptx
JohanMyburgh15
•
0 views
Putting the Human Back in the Loop: Keynote Talk at IS-EUD 2023 Cagliari
AnttiOulasvirta
•
0 views
re:Invent OPN306 AWS Lambda Powertools Lessons 10M downloads.pdf
Heitor Lessa
•
0 views
The Benefits of Serverless Architecture
MindInventory
•
0 views
AWS Lambda Powertools walkthrough.pdf
Heitor Lessa
•
0 views
01class_object_references & 02Generation_GC.pptx
ssuser95922e
•
0 views
Beating us at our own Games
Beating us at
our own Games Melvin Zhang melvin@melvinzhang.net @melvinzhangzy
CTO @ Cosmiqo
Maintainer @ MagArena,
an open source card game
Part 1: Progress
in AI and challenges
https://www.codeproject.com/Articles/1182210/Artificial-Intelligence
https://www.venturescanner.com/
Have you trained
an AI?
Have you trained
an AI?
Have you trained
an AI?
Lip reading with
LipNet, Nov 2016 http://www.cs.ox.ac.uk/news/1217-full.html
Detecting cancer cells
in biopsy, Mar 2017 https://research.googleblog.com/2017/03/assisting-pathologists-in-detecting.html
Detecting cancer cells
in biopsy, Mar 2017 https://research.googleblog.com/2017/03/assisting-pathologists-in-detecting.html
DARPA Robotics Challenge
2015 https://spectrum.ieee.org/automaton/robotics/humanoids/darpa-robotics-challenge
Part 2: Games
as a benchmark for AI
https://en.wikipedia.org/wiki/File:ST Battle Chess.png
http://afflictor.com/2012/09/11/chess-programs-regularly-play-at-good-amateur-level/
https://en.wikipedia.org/wiki/Deep Blue (chess
computer) Deep Blue
https://stockfishchess.org/ Lang:C++ License:GPLv3 Stockfish
Game tree https://en.wikipedia.org/wiki/Game tree
Optimal play Terminal min player max
player
Optimal play 1 01
1 1Terminal min player max player
Optimal play 1 01
1 1 0 Terminal min player max player
Optimal play 1 01
1 1 0 1 Terminal min player max player
Optimal play 1 01
1 1 0 1 1 Terminal min player max player
Chess has about
1046 states!
Minimax algorithm with
heuristic score Cut-off min player max player
Minimax algorithm with
heuristic score .7 .1 .6 .9Cut-off min player max player
Minimax algorithm with
heuristic score .7 .1 .6 .9 .1 Cut-off min player max player
Minimax algorithm with
heuristic score .7 .1 .6 .9 .1 .6 Cut-off min player max player
Minimax algorithm with
heuristic score .7 .1 .6 .9 .1 .6 .6 Cut-off min player max player
https://tests.stockfishchess.org/ Testing AI changes
is crucial
Scoring is hard!
http://mathworld.wolfram.com/Go.html
by Google Deepmind https://deepmind.com/research/alphago/
https://gogameguru.com/alphago-races-ahead-2-0-lee-sedol/
http://pachi.or.cz/ Lang:C License:GPLv2 Pachi
Monte Carlo evaluations Cut-off min
player max player
Monte Carlo evaluations Cut-off min
player max player
Monte Carlo evaluations Cut-off min
player max player
Monte Carlo evaluations Cut-off min
player max player
Monte Carlo evaluations Cut-off min
player max player .7
Monte Carlo Tree
Search (MCTS)
http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html MCTS + Policy
and value networks
Not all information
is known...
http://magic.wizards.com/en/events/coverage/gpsin15/father-son-2015-06-27
https://magarena.github.io Lang:Java License:GPLv3
Choose a random
instantiation of the hidden information during simulation
Challenges
Challenges https://www.linkedin.com/pulse/applying-machine-learning-security-without-phd-ken-westin/
Q&A Melvin Zhang melvin@melvinzhang.net @melvinzhangzy
Advertisement