Abstract
We introduce the open-ended, modular, self-improving Omega AI unification architecture which is a refinement of Solomonoff’s Alpha architecture, as considered from first principles. The architecture embodies several crucial principles of general intelligence including diversity of representations, diversity of data types, integrated memory, modularity, and higher-order cognition. We retain the basic design of a fundamental algorithmic substrate called an “AI kernel” for problem solving and basic cognitive functions like memory, and a larger, modular architecture that re-uses the kernel in many ways. Omega includes eight representation languages, which are briefly introduced. We review the broad software architecture, higher-order cognition, self-improvement, modular neural architectures, and intelligent agents.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alpcan, T., Everitt, T., Hutter, M.: Can we measure the difficulty of an optimization problem? In: 2014 IEEE Information Theory Workshop, ITW 2014, Hobart, Tasmania, Australia, November 2–5, 2014, pp. 356–360 (2014). https://doi.org/10.1109/ITW.2014.6970853
Hutter, M.: Universal algorithmic intelligence: a mathematical top\(\rightarrow \)down approach. In: Goertzel, B., Pennachin, C. (eds.) Artificial General Intelligence, pp. 227–290. Cognitive Technologies, Springer, Berlin (2007). https://doi.org/10.1007/978-3-540-68677-4_8
Koutník, J., Gomez, F., Schmidhuber, J.: Evolving neural networks in compressed weight space. In: Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 619–626 (2010)
Koutník, J., Gomez, F., Schmidhuber, J.: Searching for minimal neural networks in Fourier space. In: Proceedings of the 4th Annual Conference on Artificial General Intelligence. Atlantis Press (2010)
Koutník, J., Gomez, F., Schmidhuber, J.: Evolving deep/recurrent networks for reinforcement learning. In: Proceedings of the 2014 Genetic and Evolutionary Computation Conference (GECCO-2014). ACM Press (2014). to appear
Liang, J., Meyerson, E., Miikkulainen, R.: Evolutionary architecture search for deep multitask networks. arXiv preprint arXiv:1803.03745 (2018)
Özkural, E.: Towards heuristic algorithmic memory. In: Schmidhuber, J., Thórisson, K.R., Looks, M. (eds.) AGI 2011. LNCS (LNAI), vol. 6830, pp. 382–387. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-22887-2_47
Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach. Pearson Education Limited, Malaysia (2016)
Schmidhuber, J.: Gödel machines: fully self-referential optimal universal self-improvers. In: Goertzel, B., Pennachin, C. (eds.) Artificial General Intelligence, pp. 199–226. Springer, Heidelberg (2006). https://doi.org/10.1007/978-3-540-68677-4_7. variant available as arXiv:cs.LO/0309048
Solomonoff, R.J.: Progress in incremental machine learning. In: NIPS Workshop on Universal Learning Algorithms and Optimal Search, Whistler, B.C., Canada (December 2002)
Vitányi, P.M.B., Balbach, F.J., Cilibrasi, R.L., Li, M.: Normalized information distance. In: Emmert-Streib, F., Dehmer, M. (eds.) Information Theory and Statistical Learning, pp. 45–82. Springer, Boston (2009). https://doi.org/10.1007/978-0-387-84816-7_3
Weber, T., et al.: Imagination-augmented agents for deep reinforcement learning. arXiv preprint arXiv:1707.06203 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Özkural, E. (2020). Omega: An Architecture for AI Unification. In: Goertzel, B., Panov, A., Potapov, A., Yampolskiy, R. (eds) Artificial General Intelligence. AGI 2020. Lecture Notes in Computer Science(), vol 12177. Springer, Cham. https://doi.org/10.1007/978-3-030-52152-3_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-52152-3_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-52151-6
Online ISBN: 978-3-030-52152-3
eBook Packages: Computer ScienceComputer Science (R0)