Kenneth Stanley

Last updated
Kenneth O. Stanley
Alma mater University of Texas at Austin (PhD)
Known for Neuroevolution of augmenting topologies
Scientific career
Fields
Institutions
Thesis Efficient Evolution of Neural Networks Through Complexification  (2004)
Doctoral advisor Risto Miikkulainen
Website www.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]

Contents

Early life and education

Kenneth Stanley 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

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] [18]

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. [19]

Related Research Articles

Artificial intelligence (AI) is the intelligence of machines or software, as opposed to the intelligence of other living beings, primarily of humans. It is a field of study in computer science that develops and studies intelligent machines. Such machines may be called AIs.

In computational intelligence (CI), an evolutionary algorithm (EA) is a subset of evolutionary computation, a generic population-based metaheuristic optimization algorithm. An EA uses mechanisms inspired by biological evolution, such as reproduction, mutation, recombination, and selection. Candidate solutions to the optimization problem play the role of individuals in a population, and the fitness function determines the quality of the solutions. Evolution of the population then takes place after the repeated application of the above operators.

Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without explicit instructions. Recently, generative artificial neural networks have been able to surpass many previous approaches in performance.

In computer science, evolutionary computation is a family of algorithms for global optimization inspired by biological evolution, and the subfield of artificial intelligence and soft computing studying these algorithms. In technical terms, they are a family of population-based trial and error problem solvers with a metaheuristic or stochastic optimization character.

NeuroEvolution of Augmenting Topologies (NEAT) is a genetic algorithm (GA) for the generation of evolving artificial neural networks developed by Kenneth Stanley and Risto Miikkulainen in 2002 while at The University of Texas at Austin. It alters both the weighting parameters and structures of networks, attempting to find a balance between the fitness of evolved solutions and their diversity. It is based on applying three key techniques: tracking genes with history markers to allow crossover among topologies, applying speciation to preserve innovations, and developing topologies incrementally from simple initial structures ("complexifying").

In the history of artificial intelligence, neat and scruffy are two contrasting approaches to artificial intelligence (AI) research. The distinction was made in the 70s and was a subject of discussion until the middle 80s.

Neuroevolution, or neuro-evolution, is a form of artificial intelligence that uses evolutionary algorithms to generate artificial neural networks (ANN), parameters, and rules. It is most commonly applied in artificial life, general game playing and evolutionary robotics. The main benefit is that neuroevolution can be applied more widely than supervised learning algorithms, which require a syllabus of correct input-output pairs. In contrast, neuroevolution requires only a measure of a network's performance at a task. For example, the outcome of a game can be easily measured without providing labeled examples of desired strategies. Neuroevolution is commonly used as part of the reinforcement learning paradigm, and it can be contrasted with conventional deep learning techniques that use backpropagation with a fixed topology.

<span class="mw-page-title-main">AI takeover</span> Hypothetical artificial intelligence scenario

An AI takeover is a scenario in which artificial intelligence (AI) becomes the dominant form of intelligence on Earth, as computer programs or robots effectively take control of the planet away from the human species. Possible scenarios include replacement of the entire human workforce, takeover by a superintelligent AI, and the popular notion of a robot uprising. Stories of AI takeovers are very popular throughout science fiction. Some public figures, such as Stephen Hawking and Elon Musk, have advocated research into precautionary measures to ensure future superintelligent machines remain under human control.

In natural evolution and artificial evolution the fitness of a schema is rescaled to give its effective fitness which takes into account crossover and mutation.

The following outline is provided as an overview of and topical guide to artificial intelligence:

<span class="mw-page-title-main">Zoubin Ghahramani</span> British-Iranian machine learning researcher

Zoubin Ghahramani FRS is a British-Iranian researcher and Professor of Information Engineering at the University of Cambridge. He holds joint appointments at University College London and the Alan Turing Institute. and has been a Fellow of St John's College, Cambridge since 2009. He was Associate Research Professor at Carnegie Mellon University School of Computer Science from 2003–2012. He was also the Chief Scientist of Uber from 2016 until 2020. He joined Google Brain in 2020 as senior research director. He is also Deputy Director of the Leverhulme Centre for the Future of Intelligence.

<span class="mw-page-title-main">NEAT Particles</span>

NEAT Particles is an interactive evolutionary computation program that enables users to evolve particle systems intended for use as special effects in video games or movie graphics. Rather than being hand-coded like typical particle systems, the behaviors of NEAT Particle effects are evolved by user preference. Therefore, non-programmer, non-artist users may evolve complex and unique special effects in real time. NEAT Particles is meant to augment and assist the time-consuming computer graphics content generation process. NEAT is short for Neuroevolution of Augmenting Topologies.

Compositional pattern-producing networks (CPPNs) are a variation of artificial neural networks (ANNs) that have an architecture whose evolution is guided by genetic algorithms.

Dr Peter John Bentley is a British author and computer scientist based at University College London.

<span class="mw-page-title-main">HyperNEAT</span>

Hypercube-based NEAT, or HyperNEAT, is a generative encoding that evolves artificial neural networks (ANNs) with the principles of the widely used NeuroEvolution of Augmented Topologies (NEAT) algorithm developed by Kenneth Stanley. It is a novel technique for evolving large-scale neural networks using the geometric regularities of the task domain. It uses Compositional Pattern Producing Networks (CPPNs), which are used to generate the images for Picbreeder.orgArchived 2011-07-25 at the Wayback Machine and shapes for EndlessForms.comArchived 2018-11-14 at the Wayback Machine. HyperNEAT has recently been extended to also evolve plastic ANNs and to evolve the location of every neuron in the network.

<span class="mw-page-title-main">Georgios N. Yannakakis</span>

Georgios N. Yannakakis is Director and Professor at the Institute of Digital Games, University of Malta and Editor-in-Chief of IEEE Transactions on Games. He is one of the leading researchers within player affective modelling and adaptive content generation for games. He is considered one of the most accomplished experts at the intersection of games and AI.

<i>Galactic Arms Race</i> 2010 video game

Galactic Arms Race (GAR) is a space shooter video game first released in 2010 by American studio Evolutionary Games in association with the Evolutionary Complexity Research Group at UCF (EPlex).

Risto Miikkulainen is a Finnish-American computer scientist and professor at the University of Texas at Austin. He is also an AVP of Evolutionary AI at Cognizant. In 2023, he was elected an AAAI Fellow "for significant contribution to neuroevolution techniques and applications", and in 2016, named Fellow of the Institute of Electrical and Electronics Engineers (IEEE) "for contributions to techniques and applications for neural and evolutionary computation". He was elected a Fellow of the Association for the Advancement of Artificial Intelligence in 2023. Born in Helsinki, Finland, Miikkulainen has lived in the United States since 1986.

Artificial intelligence and machine learning techniques are used in video games for a wide variety of applications such as non-player character (NPC) control and procedural content generation (PCG). Machine learning is a subset of artificial intelligence that uses historical data to build predictive and analytical models. This is in sharp contrast to traditional methods of artificial intelligence such as search trees and expert systems.

References

  1. 1 2 3 Aschwanden, Christie (23 July 2015). "Stop Trying To Be Creative". FiveThirtyEight. Retrieved 5 April 2022.
  2. 1 2 "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. 1 2 "Uber acquires Geometric Intelligence to create an AI lab". TechCrunch. Retrieved 31 May 2022.
  8. 1 2 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. 1 2 "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. ↑ Harris, Jeremie (24 November 2021). "AI without Objectives". Medium. Towards Data Science. Retrieved 9 June 2022.
  19. ↑ "2017 ISAL Awards: Winners". Artificial Life. 16 September 2017. Retrieved 9 June 2022.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.