Search Results

You are looking at 1 - 5 of 5 items for :

  • direct search methods x
  • Artificial Intelligence x
Clear All
Open access

Brandon Rohrer

Accelerating progress in Artificial General Intelligence: Choosing a benchmark for natural world interaction

Measuring progress in the field of Artificial General Intelligence (AGI) can be difficult without commonly accepted methods of evaluation. An AGI benchmark would allow evaluation and comparison of the many computational intelligence algorithms that have been developed. In this paper I propose that a benchmark for natural world interaction would possess seven key characteristics: fitness, breadth, specificity, low cost, simplicity, range, and task focus. I also outline two benchmark examples that meet most of these criteria. In the first, the direction task, a human coach directs a machine to perform a novel task in an unfamiliar environment. The direction task is extremely broad, but may be idealistic. In the second, the AGI battery, AGI candidates are evaluated based on their performance on a collection of more specific tasks. The AGI battery is designed to be appropriate to the capabilities of currently existing systems. Both the direction task and the AGI battery would require further definition before implementing. The paper concludes with a description of a task that might be included in the AGI battery: the search and retrieve task.

Open access

G. Papaioannou and J.M. Wilson

.Y. and Ip, W.H. (2003). A heuristic algorithm for machine assignment in cellular layout, Computers and Industrial Engineering , 44, 49-73. [10] Chan, H.M. and Milner, D.A. (1982). Direct clustering algorithm for group formation in cellular manufacturing, Journal of Manufacturing Systems , 1 (1), 65-75. [11] Congawave, T. and Ham, I. (1981). Cluster analysis applications for group technology manufacturing systems, Proceedings, North American Manufacturing Research Conference (NAMRC), 9 T H (Dearborn) , 65-75. [12] De

Open access

Maciej Rossa and Mariusz Rogulski

References [1] Act of 27 April 2001 Environmental Protection Law. [2] Chen N., Hu C., Chen Y., Wang C., Gong J., Using SensorML to construct a geoprocessing e-Science workflow model under a sensor web environment, Computers & Geosciences , 47 , 2012, 119–129. [3] Chen N., Wang X., Yang X., A direct registry service method for sensors and algorithms based on the process model, Computers & Geosciences , 56 , 2013, 45–55. [4] Compton M., Barnaghi P., Bermudez L., García-Castro R., Corcho O., Coxe S., Graybeal J., Hauswirth M., Hensonh C

Open access

Marta Szachniuk

References [1] Adamiak R.W., Blazewicz J., Formanowicz P., Gdaniec Z., Kasprzak M., Popenda M., Szachniuk M., An algorithm for an automatic NOE pathways analysis of 2D NMR spectra of RNA duplexes, Journal of Computational Biology, 11 , 2004, 163-180. [2] Antczak M., Blazewicz J., Lukasiak P., Milostan M., Krasnogor N., Palik G., DomAns-Pattern based method for protein domain boundaries prediction and analysis, Foundations of Computing and Decision Sciences , 36 , 2011, 99-119. [3] Antczak M., Zok T., Popenda M., Lukasiak P., Adamiak R

Open access

Karol Basiński, Bartłomiej Ufnalski and Lech M. Grzesiak

rzesiak L.M., Plug-in direct multi-swarm repetitive controller for the sine wave inverter – on keeping particles diversified in a dynamic and noisy environment , 6th Int. Conf. Power Engineering, Energy and Electrical Drives, 10th Int. Conf. Compatibility and Power Electronics (CPE-POWERENG), Poland, 2016, 484–491. [20] U fnalski B., M ałkowski M., G rzesiak L.M., Hybrid repetitive controller using a stochastic evolutionary search and a deterministic iterative learning law , 21st Int. Conf. Methods and Models in Automation and Robotics MMAR 2016, Poland