Post on 25-Sep-2020
A Few AI Achievements
Amy Greenwald, Enrique Areyan ViqueiraCS140 - Fall 2020 - The COVID year
AI Achievements
AI techniques are used in MANY places for MANY purposes.
Let’s take a walk on our syllabus for the semester.
Search
Adversarial Search in Games
Optimization
Hidden Markov Models
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Natural Language Processing
Computer Vision
Multi-agent Systems
AI Achievements
AI techniques are used in MANY places for MANY purposes.
Let’s take a walk on our syllabus for the semester.
Search
Adversarial Search in Games
Optimization
Hidden Markov Models
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Natural Language Processing
Computer Vision
Multi-agent Systems
}Core Topics
AI Achievements
AI techniques are used in MANY places for MANY purposes.
Let’s take a walk on our syllabus for the semester.
Search
Adversarial Search in Games
Optimization
Hidden Markov Models
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Natural Language Processing
Computer Vision
Multi-agent Systems
}Core Topics
{Invited Speakers
AI Achievements - Search
AI Achievements - Search
AI Achievements - Search
AI Achievements - Search
AI Achievements - Search
AI Achievements - Adversarial Search in Games
AI Achievements - Adversarial Search in Games
AI Achievements - Adversarial Search in Games
AI Achievements - Adversarial Search in Games
AI Achievements - Adversarial Search in Games
AI Achievements - Adversarial Search in Games
AI Achievements - Adversarial Search in Games
https://vimeo.com/389556398
AI Achievements - Optimization
SAT: Satisfiability, checking whether a boolean formula e.g,
can be satisfied or not.(x1 ∨ x2) ∧ (¬x1 ∨ x3)
AI Achievements - Optimization
SAT: Satisfiability, checking whether a boolean formula e.g,
can be satisfied or not.(x1 ∨ x2) ∧ (¬x1 ∨ x3)
AI Achievements - Optimization
SAT: Satisfiability, checking whether a boolean formula e.g,
can be satisfied or not.(x1 ∨ x2) ∧ (¬x1 ∨ x3)
AI Achievements - Optimization
SAT: Satisfiability, checking whether a boolean formula e.g,
can be satisfied or not.(x1 ∨ x2) ∧ (¬x1 ∨ x3)
AI Achievements - Optimization
Also, Operations Research
SAT: Satisfiability, checking whether a boolean formula e.g,
can be satisfied or not.(x1 ∨ x2) ∧ (¬x1 ∨ x3)
AI Achievements - Hidden Markov Models
AI Achievements - Hidden Markov Models
AI Achievements - Hidden Markov Models
AI Achievements - Hidden Markov Models
AI Achievements - Hidden Markov Models
AI Achievements - Hidden Markov Models
AI Achievements - Supervised Learning
AI Achievements - Supervised Learning
AI Achievements - Supervised Learning
AI Achievements - Supervised Learning
AI Achievements - Supervised Learning
AI Achievements - Supervised Learning
AI Achievements - Supervised Learning
AI Achievements - Supervised Learning
https://thispersondoesnotexist.com
AI Achievements - Unsupervised Learning
AI Achievements - Unsupervised Learning
AI Achievements - Unsupervised Learning
AI Achievements - Unsupervised Learning
AI Achievements - Reinforcement Learning
AI Achievements - Reinforcement Learning
AI Achievements - Reinforcement Learning
AI Achievements - Reinforcement Learning
AI Achievements - Reinforcement Learning
AI Achievements - Reinforcement Learning
AI Achievements - Natural Language Processing
AI Achievements - Natural Language Processing
AI Achievements - Natural Language Processing
A universal translator. Instant translation of any language to any other!
AI Achievements - Natural Language Processing
A universal translator. Instant translation of any language to any other!
AI Achievements - Natural Language Processing
A universal translator. Instant translation of any language to any other!
AI Achievements - Computer Vision
AI Achievements - Computer Vision
AI Achievements - Computer Vision
AI Achievements - Computer Vision
AI Achievements - Multi-agent Systems
AI Achievements - Vision + Actions + Planning +…
Source The Batch Newsletter.
AI Achievements - Vision + Actions + Planning +…
Source The Batch Newsletter.
AI Achievements - But how to put it all together?
AI Achievements - But how to put it all together?
Shakey
AI Achievements - But how to put it all together?
Shakey The Future?
References
Search
Klein, D., & Manning, C. D. (2003, May). A parsing: fast exact Viterbi parse selection. In Proceedings of
the 2003 Conference of the North American Chapter of the Association for Computational Linguistics
on Human Language Technology-Volume 1 (pp. 40-47). Association for Computational Linguistics.
Duchoň, F., Babinec, A., Kajan, M., Beňo, P., Florek, M., Fico, T., & Jurišica, L. (2014). Path planning with
modified a star algorithm for a mobile robot. Procedia Engineering, 96, 59-69.
Adversarial Search
Newborn, M. (2012). Kasparov versus Deep Blue: Computer chess comes of age. Springer Science &
Business Media.
Moravčík, M., Schmid, M., Burch, N., Lisý, V., Morrill, D., Bard, N., ... & Bowling, M. (2017). Deepstack:
Expert-level artificial intelligence in heads-up no-limit poker. Science, 356(6337), 508-513.
Silver, D., Schrittwieser, J., Simonyan, K., Antonoglou, I., Huang, A., Guez, A., ... & Chen, Y. (2017).
Mastering the game of go without human knowledge. nature, 550(7676), 354-359.
https://twitter.com/Kasparov63/status/1227391767584092160
References
Optimization
Davis, M., Logemann, G., & Loveland, D. (1962). A machine program for theorem-proving.
Communications of the ACM, 5(7), 394-397.
Gomes, C. P., Kautz, H., Sabharwal, A., & Selman, B. (2008). Satisfiability solvers.
Foundations of Artificial Intelligence, 3, 89-134.
https://satcompetition.github.io/2020/
Hidden Markov Models
Mamon, R. S., & Elliott, R. J. (Eds.). (2007). Hidden Markov models in finance (Vol. 4). New
York: Springer.
Sonnhammer, E. L., Von Heijne, G., & Krogh, A. (1998, July). A hidden Markov model for
predicting transmembrane helices in protein sequences. In Ismb (Vol. 6, pp. 175-182).
Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in
speech recognition. Proceedings of the IEEE, 77(2), 257-286.
References
Supervised Learning
Soni, J., Ansari, U., Sharma, D., & Soni, S. (2011). Predictive data mining for
medical diagnosis: An overview of heart disease prediction. International Journal
of Computer Applications, 17(8), 43-48.
Unsupervised Learning
Turney, P. D. (2002). Thumbs up or thumbs down? Semantic orientation applied
to unsupervised classification of reviews. arXiv preprint cs/0212032.
Oyelade, O. J., Oladipupo, O. O., & Obagbuwa, I. C. (2010). Application of k
Means Clustering algorithm for prediction of Students Academic Performance.
arXiv preprint arXiv:1002.2425.
Sculley, D. (2010, April). Web-scale k-means clustering. In Proceedings of the
19th international conference on World wide web (pp. 1177-1178).
References
Reinforcement Learning
Silver, D., Schrittwieser, J., Simonyan, K., Antonoglou, I., Huang, A., Guez, A., ... & Chen, Y.
(2017). Mastering the game of go without human knowledge. nature, 550(7676), 354-359.
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller,
M. (2013). Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602.
Abbeel, P., Coates, A., Quigley, M., & Ng, A. Y. (2007). An application of reinforcement
learning to aerobatic helicopter flight. In Advances in neural information processing
systems (pp. 1-8).
Ipek, E., Mutlu, O., Martínez, J. F., & Caruana, R. (2008). Self-optimizing memory controllers:
A reinforcement learning approach. ACM SIGARCH Computer Architecture News, 36(3),
39-50.
Li, L., Chu, W., Langford, J., & Schapire, R. E. (2010, April). A contextual-bandit approach to
personalized news article recommendation. In Proceedings of the 19th international
conference on World wide web (pp. 661-670).
References
Multi-agent Systems
Kitano, H., & Tadokoro, S. (2001). Robocup rescue: A grand
challenge for multiagent and intelligent systems. AI magazine,
22(1), 39-39.
Image Credits
https://en.wikipedia.org/wiki/Google_Maps_pin
https://www.thehoneymoondestinations.com/best-flight-search-engines-sites-for-booking-cheap-
airfare/
https://www.deepstack.ai/
https://www.dailymail.co.uk/sciencetech/article-3950698/Why-toddlers-REALLY-love-play-hide-seek-
Young-brains-believe-really-invisible-hands.html
http://historyoflinearalgebra.weebly.com/andrey-markov-pdb.html
https://techcrunch.com/2018/05/14/you-can-now-try-smart-compose-in-the-new-gmail/
https://algorithmxlab.com/blog/computer-vision/
https://en.wikipedia.org/wiki/Tower_of_Babel
https://ph.news.yahoo.com/real-life-ai-rivals-star-wars-universal-translator-141610791.html
https://www.computerweekly.com/photostory/450423802/AI-A-brief-history-of-man-versus-machine-
intelliegnce/3/IBM-Watson-versus-Jeopardy
https://cosmosmagazine.com/technology/robocup-2017-wrap-up-highs-lows-plenty-of-falls/
https://frc.ri.cmu.edu/~hpm/project.archive/robot.papers/2000/revo.slides/1970.html
https://www.john-adams.nl/october-26-2014-soft-machines-deception/