2014 Proceeding- Editor-in-chief:
- Christian Igel,
- General Chair:
- Dirk V. Arnold
On behalf of the Organizing Committee, I would like to welcome you to Vancouver for the 2014 Genetic and Evolutionary Computation Conference (GECCO 2014). This years GECCO is comprised of 20 tracks, including the new Artificial Immune Systems and Hot Off the Press (HOP) tracks. The latter offers authors of outstanding research recently published in journals and other conferences the opportunity to present their work to the GECCO community. Under the guidance of Editor-in-Chief Christian Igel, the Track Chairs and Program Committee have selected 180 out of the 544 submissions received in all tracks (excluding HOP) for oral presentation as full papers, resulting in an acceptance rate of 33%. Close to 100 short papers will be presented in the poster session.
Highlights of the conference include keynote talks by Yoshua Bengio on "Deep Learning and Cultural Evolution", and by Dario Floreano on "Bridging Natural and Artificial Evolution", as well as an invited talk by Sumit Gulwani in the Genetic Programming track. Altogether 32 tutorials cover topics ranging from broad and introductory to specialized and at the frontier of current research. GECCO also hosts fifteen workshops, including several new ones as well as at least one that predates GECCO itself. Further high points include the 11th Annual "Humies" Awards for Human- Competitive Results, which are again generously supported by John Koza, and five competitions, ranging from Art, Design, and Creativity to the Industrial Challenge. Finally, Evolutionary Computation in Practice continues to be an important and integral part of GECCO.
There and back again: gene-processing hardware for the evolution and robotic deployment of robust navigation strategies
Navigation strategies represent some of the most intriguing examples of complex and intelligent behaviors in nature. Accordingly, they have been the focus of extensive research in animal behavior and in evolutionary robotics. However, engineering ...
Evolving neural networks that are both modular and regular: HyperNEAT plus the connection cost technique
One of humanity's grand scientific challenges is to create artificially intelligent robots that rival natural animals in intelligence and agility. A key enabler of such animal complexity is the fact that animal brains are structurally organized in that ...
Trading control intelligence for physical intelligence: muscle drives in evolved virtual creatures
Traditional evolved virtual creatures [1] are actuated using unevolved, uniform, invisible drives at joints between rigid segments. In contrast, this paper shows how such conventional actuators can be replaced by evolvable muscle drives that are a part ...
Guided self-organization in indirectly encoded and evolving topographic maps
An important phenomenon seen in many areas of biological brains and recently in deep learning architectures is a process known as self-organization. For example, in the primary visual cortex, color and orientation maps develop based on lateral ...
Some distance measures for morphological diversification in generative evolutionary robotics
Evolutionary robotics often involves optimization in large, complex search spaces, requiring good population diversity. Recently, measures to actively increase diversity or novelty have been employed in order to get sufficient exploration of the search ...
Growth in co-evolution of sensory system and signal processing for optimal wing control
The development of adaptive systems, which react autonomously to changes in their environment, require the coordinated generation of sensors, providing information about the environment and signal processing structures, which generate suitable reactions ...
Novelty search creates robots with general skills for exploration
Novelty Search, a new type of Evolutionary Algorithm, has shown much promise in the last few years. Instead of selecting for phenotypes that are closer to an objective, Novelty Search assigns rewards based on how different the phenotypes are from those ...
A continuous developmental model for wind farm layout optimization
We present DevoII, an improved cell-based developmental model for wind farm layout optimization. To address the shortcomings of discretization, DevoII's gene regulatory networks control cells that act in a continuous rather than discretized grid space. ...
Cited By
-
Zheng Y, Peng N, Qi H, Gong G, Huang D, Zhu K, Liu J and Liu G (2024). An improved memetic algorithm for distributed hybrid flow shop scheduling problem with operation inspection and reprocessing, Measurement and Control, 10.1177/00202940241245241
-
Solo A (2023). Curriculum for a New Five-Year Academic Program in Intelligent Systems Engineering and Software Engineering 2023 International Conference on Computational Science and Computational Intelligence (CSCI), 10.1109/CSCI62032.2023.00280, 979-8-3503-6151-3, (1700-1707)
- Jansen T On the Black-Box Complexity of Example Functions Proceedings of the 2015 ACM Conference on Foundations of Genetic Algorithms XIII, (16-24)
Index Terms
- Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation
Recommendations
Acceptance Rates
| Year | Submitted | Accepted | Rate |
|---|---|---|---|
| GECCO '17 | 462 | 178 | 39% |
| GECCO '16 | 381 | 137 | 36% |
| GECCO '16 Companion | 381 | 137 | 36% |
| GECCO '15 | 505 | 182 | 36% |
| GECCO '14 | 544 | 180 | 33% |
| GECCO Comp '14 | 544 | 180 | 33% |
| GECCO '13 | 570 | 204 | 36% |
| GECCO '07 | 577 | 266 | 46% |
| GECCO '06 | 446 | 205 | 46% |
| Overall | 4,410 | 1,669 | 38% |