Omega: An Architecture for AI Unification

We introduce the open-ended, modular, selfimproving 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 and six classes of neural networks, which are briefly introduced. The architecture is intended to initially address data science automation, hence it includes many problem solving methods for statistical tasks. We review the broad software architecture, higher-order cognition, self-improvement, modular neural architectures, intelligent agents, the process and memory hierarchy, hardware abstraction, peerto-peer computing, and data abstraction facility.

[1]  Ulrike von Luxburg,et al.  Proceedings of the 28th International Conference on Machine Learning, ICML 2011 , 2011, International Conference on Machine Learning.

[2]  Fionn Murtagh,et al.  Ward’s Hierarchical Agglomerative Clustering Method: Which Algorithms Implement Ward’s Criterion? , 2011, Journal of Classification.

[3]  L. Christophorou.  Science , 2018, Emerging Dynamics: Science, Energy, Society and Values.

[4]  Jürgen Schmidhuber,et al.  Multi-column deep neural network for traffic sign classification , 2012, Neural Networks.

[5]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Elliot Meyerson,et al.  Evolutionary architecture search for deep multitask networks , 2018, GECCO.

[7]  A. Hanks.  Canada , 2002 .

[8]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[9]  Ke Zhang,et al.  Video Summarization with Long Short-Term Memory , 2016, ECCV.

[10]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[11]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[12]  Marcus Hutter,et al.  Universal Algorithmic Intelligence: A Mathematical Top→Down Approach , 2007, Artificial General Intelligence.

[13]  James M. Landwehr.  The American Statistician, Editor's Report for 1998 , 1999 .

[14]  Jürgen Schmidhuber,et al.  Gödel Machines: Fully Self-referential Optimal Universal Self-improvers , 2007, Artificial General Intelligence.

[15]  D. Cox.  The Regression Analysis of Binary Sequences , 2017 .

[16]  Christophe Andrieu,et al.  31st International Conference on Machine Learning, ICML 2014 , 2014, International Conference on Machine Learning.

[17]  Joshua B. Tenenbaum,et al.  Picture: A probabilistic programming language for scene perception , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Joshua B. Tenenbaum,et al.  Deep Convolutional Inverse Graphics Network , 2015, NIPS.

[19]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[20]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[21]  Razvan Pascanu,et al.  Imagination-Augmented Agents for Deep Reinforcement Learning , 2017, NIPS.

[22]  Joshua B. Tenenbaum,et al.  Church: a language for generative models , 2008, UAI.

[23]  M. V. Rossum,et al.  In Neural Computation , 2022 .

[24]  Jürgen Schmidhuber,et al.  Searching for Minimal Neural Networks in Fourier Space , 2010, AGI 2010.

[25]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[26]  H. J. Mclaughlin,et al.  Learn , 2002 .

[27]  Jürgen Schmidhuber,et al.  Evolving neural networks in compressed weight space , 2010, GECCO '10.

[28]  Tansu Alpcan,et al.  Can we measure the difficulty of an optimization problem? , 2014, 2014 IEEE Information Theory Workshop (ITW 2014).

[29]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Yoram Singer,et al.  The Hierarchical Hidden Markov Model: Analysis and Applications , 1998, Machine Learning.

[31]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[32]  Michael I. Jordan,et al.  On Convergence Properties of the EM Algorithm for Gaussian Mixtures , 1996, Neural Computation.

[33]  Zhe Gan,et al.  Variational Autoencoder for Deep Learning of Images, Labels and Captions , 2016, NIPS.

[34]  Xiang Zhang,et al.  Character-level Convolutional Networks for Text Classification , 2015, NIPS.