Artificial General Intelligence

Against the backdrop of increasing progresses in AI research paired with a rise of AI applications in decision-making processes, security-critical domains as well as in ethically relevant frames, a largescale debate on possible safety measures encompassing corresponding long-term and short-term issues has emerged across different disciplines. One pertinent topic in this context which has been addressed by various AI Safety researchers is e.g. the AI alignment problem for which no final consensus has been achieved yet. In this paper, we present a multidisciplinary toolkit of AI Safety strategies combining considerations from AI and Systems Engineering as well as from Cognitive Science with a security mindset as often relevant in Cybersecurity. We elaborate on how AGI “Self-awareness” could complement different AI Safety measures in a framework extended by a jointly performed Human Enhancement procedure. Our analysis suggests that this hybrid framework could contribute to undertake the AI alignment problem from a new holistic perspective through security-building synergetic effects emerging thereof and could help to increase the odds of a possible safe future transition towards superintelligent systems.

[1]  Adam Krzyzak,et al.  Performance Evaluation of the Silhouette Index , 2015, ICAISC.

[2]  Ben Goertzel,et al.  Learning Language from a Large (Unannotated) Corpus , 2014, ArXiv.

[3]  Denis Lalanne,et al.  “Our Inherent Desire for Control”: a Case Study of Automation’s Impact on the Perception of Comfort , 2017 .

[4]  Barbara H. Partee,et al.  Workshop on Information and Representation Report. , 1985 .

[5]  Daniel Dominic Sleator,et al.  Parsing English with a Link Grammar , 1995, IWPT.

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

[7]  H. Garfinkel.  Studies in Ethnomethodology , 1968 .

[8]  Ben Goertzel,et al.  Engineering General Intelligence, Part 2: The CogPrime Architecture for Integrative, Embodied AGI , 2014 .

[9]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[10]  Alexey Potapov,et al.  Real-Time GA-Based Probabilistic Programming in Application to Robot Control , 2016, AGI.

[11]  W. Quine.  The two dogmas of empiricism , 1951 .

[12]  Matus Telgarsky,et al.  Benefits of Depth in Neural Networks , 2016, COLT.

[13]  Marc'Aurelio Ranzato,et al.  Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Emmanuel Dupoux,et al.  Cognitive science in the era of artificial intelligence: A roadmap for reverse-engineering the infant language-learner , 2016, Cognition.

[15]  Anton Kolonin,et al.  Automatic text classification and property extraction applications in medicine , 2015, 2015 International Conference on Biomedical Engineering and Computational Technologies (SIBIRCON).

[16]  H. Knoblauch,et al.  Video analysis: methodology and methods , 2006 .

[17]  Joel Friedman,et al.  Sheaves on Graphs, Their Homological Invariants, and a Proof of the Hanna Neumann Conjecture , 2011, 1105.0129.

[18]  Denis Lalanne,et al.  Deconstructing human-building interaction , 2016, Interactions.

[19]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[20]  David A. Ross,et al.  Wearable interfaces for orientation and wayfinding , 2000, Assets '00.

[21]  Luis Mateus Rocha,et al.  Singular value decomposition and principal component analysis , 2003 .

[22]  Huiying Shen,et al.  A mobile phone system to find crosswalks for visually impaired pedestrians. , 2008, Technology and disability.

[23]  H. T. Kung,et al.  Language Modeling by Clustering with Word Embeddings for Text Readability Assessment , 2017, CIKM.

[24]  Denis Lalanne,et al.  From Artifacts to Architecture , 2018, Conference on Designing Interactive Systems.

[25]  Deniz Yuret,et al.  Discovery of linguistic relations using lexical attraction , 1998, ArXiv.

[26]  Ray J. Solomonoff,et al.  Complexity-based induction systems: Comparisons and convergence theorems , 1978, IEEE Trans. Inf. Theory.

[27]  R. Solomonoff.  A SYSTEM FOR INCREMENTAL LEARNING BASED ON ALGORITHMIC PROBABILITY , 1989 .

[28]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[29]  Ben Goertzel,et al.  OpenCog: A Software Framework for Integrative Artificial General Intelligence , 2008, AGI.

[30]  D. Sculley,et al.  Web-scale k-means clustering , 2010, WWW '10.

[31]  Bartunov Sergey,et al.  Breaking Sticks and Ambiguities with Adaptive Skip-gram , 2016 .

[32]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

[33]  C. S. Wallace,et al.  An Information Measure for Classification , 1968, Comput. J..

[34]  Denis Lalanne,et al.  Is Driverless Car Another Weiserian Mistake? , 2017, Conference on Designing Interactive Systems.

[35]  John D. Kelleher,et al.  An Analysis of the Application of Simplified Silhouette to the Evaluation of k-means Clustering Validity , 2017, MLDM.

[36]  Julian Togelius,et al.  Neuroevolution in Games: State of the Art and Open Challenges , 2014, IEEE Transactions on Computational Intelligence and AI in Games.

[37]  Jean-François Delpech.  Unsupervised word sense disambiguation in dynamic semantic spaces , 2018, ArXiv.

[38]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[39]  David L. Dowe,et al.  Minimum Message Length and Kolmogorov Complexity , 1999, Comput. J..

[40]  Razvan Pascanu,et al.  A simple neural network module for relational reasoning , 2017, NIPS.

[41]  Klaus Krippendorff,et al.  Content Analysis: An Introduction to Its Methodology , 1980 .

[42]  Denis Lalanne,et al.  Future of Human-Building Interaction , 2016, CHI Extended Abstracts.

[43]  Jürgen Schmidhuber,et al.  Optimal Ordered Problem Solver , 2002, Machine Learning.

[44]  N. Fairclough.  Analysing Discourse: Textual Analysis for Social Research , 2003 .

[45]  Razvan Pascanu,et al.  Progressive Neural Networks , 2016, ArXiv.

[46]  Naftali Tishby,et al.  Deep learning and the information bottleneck principle , 2015, 2015 IEEE Information Theory Workshop (ITW).