Jump to content

Kenneth Stanley

From Wikipedia, the free encyclopedia
Kenneth O. Stanley
Alma materUniversity of Texas at Austin (PhD)
Known forNeuroevolution of augmenting topologies
Scientific career
Fields
Institutions
ThesisEfficient Evolution of Neural Networks Through Complexification (2004)
Doctoral advisorRisto Miikkulainen
Websitewww.cs.ucf.edu/~kstanley/

Kenneth Owen Stanley is an artificial intelligence researcher, author, and former professor of computer science at the University of Central Florida known for creating the Neuroevolution of augmenting topologies (NEAT) algorithm. He coauthored Why Greatness Cannot Be Planned: The Myth of the Objective with Joel Lehman which argues for the existence of the "objective paradox", a paradox which states that "soon as you create an objective, you ruin your ability to reach it".[1] While a professor at the University of Central Florida, he was the director of the Evolutionary Complexity Research Group (EPlex)[2] which led the development of Galactic Arms Race. He also developed the HyperNEAT,[3] CPPNs,[4] and novelty search[5] algorithms.[6] He also co-founded Geometric Intelligence, an AI research firm, in 2015.[7][8]

Early life and education

[edit]

Kenneth Stanley is the son of Richard P. Stanley. He became interested in computer programming at the age of 8 during a summer camp. He later pursued his interest by taking AP Computer Science at Newton South High School and majoring in Computer Science at the University of Pennsylvania, graduating in 1997. He received his PhD from the University of Texas at Austin under Risto Miikkulainen in 2004 for his work developing the Neuroevolution of augmenting topologies (NEAT) algorithm.[9][10]

Work

[edit]

In 2006, he became an associate professor of Computer Science at the University of Central Florida and later became a Charles Millican Professor in 2017.[11]

In 2007, he created PicBreeder, a piece of software that uses NEAT to allow users to evolve pictures by randomly generating images and having the user pick which image will produce children. This allows users to shape random blobs into recognizable shapes like animals or cars. Watching the algorithm evolve what appeared to be a pair of alien eyes into an image that looked like a car led Stanley to realize that nearly every interesting image on PicBreeder evolved by way of a different looking image. This led him to develop what he calls the steppingstone principle that, "Instead of hard-coding the rules of reasoning, or having computers learn to score highly on specific performance metrics ... we must let a population of solutions blossom. Make them prioritize novelty or interestingness instead of the ability to walk or talk. They may discover an indirect path, a set of steppingstones, and wind up walking and talking better than if they’d sought those skills directly."[1][12]

As the director of EPlex, he then served as the faculty advisor and as a software developer for Erin Hastings' Galactic Arms Race. First released in 2010, it is a space shooter that uses cgNEAT technology. cgNEAT or "content generating NEAT" is a variant of NEAT developed by Hastings and Stanley that "automatically generates graphical and game content while the game is played, based on the past preferences of the players".[2][13][14]

In 2015, he coauthored Why Greatness Cannot Be Planned: The Myth of the Objective with Joel Lehman. Inspired by his work with PicBreeder and other research, they discuss how intentionally perusing objectives can limit your success at achieving them, both for people and AI. According to the book, perusing novelty instead of an objective is more likely to succeed in creative tasks.[1] They argue that this could be a more effective way of funding scientific research or could as a way of running a business.[15] It received positive reviews with one reviewer writing that, "If you are yearning to do what’s interesting, rather than optimizing a 'metric' of approach to a prescribed 'objective', you will love this book."[16]

In 2015, he co-founded Geometric Intelligence a private research and development firm focusing on artificial intelligence and machine learning with Gary Marcus, Zoubin Ghahramani, and Doug Bemis.[8] Uber acquired the firm in late 2016 and renamed it to Uber AI labs.[7] He continued working at the firm after its acquisition as a senior research science manager and the head of Core AI research.[17] He left both Uber AI Labs and the University of Central Florida in 2020 to lead the Open-Endedness team at OpenAI as a Research Science Manager.[11] In 2017, Stanley won the 2017 ISAL Award for Outstanding Paper of the Decade 2002 – 2012 for his original 2002 NEAT paper with Risto Miikkulainen.[18]

References

[edit]
  1. ^ a b c Aschwanden, Christie (23 July 2015). "Stop Trying To Be Creative". FiveThirtyEight. Retrieved 5 April 2022.
  2. ^ a b "EPlex People". eplex.cs.ucf.edu. Retrieved 5 April 2022.
  3. ^ Stanley, Kenneth O.; D'Ambrosio, David B.; Gauci, Jason (2009-01-14). "A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks". Artificial Life. 15 (2): 185–212. doi:10.1162/artl.2009.15.2.15202. ISSN 1064-5462. PMID 19199382. S2CID 26390526. Retrieved 30 May 2022.
  4. ^ Kenneth O. Stanley (2007). "Compositional Pattern Producing Networks: A Novel Abstraction of Development" (PDF). Genetic Programming and Evolvable Machines. 8 (2): 131–162. CiteSeerX 10.1.1.643.8179. doi:10.1007/s10710-007-9028-8. S2CID 2535195. Retrieved 30 May 2022.
  5. ^ Lehman, Joel; Stanley, Kenneth O. (June 2011). "Abandoning Objectives: Evolution Through the Search for Novelty Alone". Evolutionary Computation. 19 (2): 189–223. doi:10.1162/EVCO_a_00025. ISSN 1063-6560. PMID 20868264. S2CID 12129661. Retrieved 30 May 2022.
  6. ^ "Uber Engineering Blog". Uber Engineering Blog. 30 June 2020. Retrieved 30 May 2022.
  7. ^ a b "Uber acquires Geometric Intelligence to create an AI lab". TechCrunch. Retrieved 31 May 2022.
  8. ^ a b Schlueb, Mark (3 July 2017). "UCF Professor Talks About Why Uber Acquired His Tech Startup". University of Central Florida News | UCF Today. Retrieved 9 June 2022.
  9. ^ "Artificial Intelligence Q&A With Kenneth Stanley". Orlando Science Center. 20 November 2019. Retrieved 30 May 2022.
  10. ^ Stanley, Kenneth O. (2004). "Efficient Evolution of Neural Networks Through Complexification". Department of Computer Sciences, the University of Texas at Austin. Retrieved 30 May 2022.
  11. ^ a b "Kenneth Stanley - San Francisco, California, United States". linkedin. Retrieved 9 June 2022.
  12. ^ Hutson, Matthew (6 November 2019). "Computers Evolve a New Path Toward Human Intelligence". Quanta Magazine. Retrieved 9 June 2022.
  13. ^ Hastings, Erin Jonathan; Guha, Ratan K.; Stanley, Kenneth O. (December 2009). "Automatic Content Generation in the Galactic Arms Race Video Game". IEEE Transactions on Computational Intelligence and AI in Games. 1 (4): 245–263. doi:10.1109/TCIAIG.2009.2038365. ISSN 1943-0698. S2CID 88411. Retrieved 9 June 2022.
  14. ^ Fleming, Jeffrey (April 2010). "Galactic Arms Race: Evolving the Shooter" (PDF). Game Developer Magazine. Retrieved 9 June 2022.
  15. ^ Smart, Andrew J. (17 March 2016). "How Overfocusing on Goals Can Hold Us Back". Harvard Business Review. Retrieved 9 June 2022.
  16. ^ Hersh, Reuben (July 2015). "Novelty Wins, "Straight Toward Objective" Loses! or Book Review: Why Greatness Cannot Be Planned: The Myth of the Objective, by Kenneth O. Stanley and Joel Lehman". Journal of Humanistic Mathematics. 5 (2): 161–165. doi:10.5642/jhummath.201502.15.
  17. ^ "Kenneth O. Stanley". O’Reilly Media. Retrieved 9 June 2022.
  18. ^ "2017 ISAL Awards: Winners". Artificial Life. 16 September 2017. Retrieved 9 June 2022.
[edit]