Publications

Journal Articles

  • van Oostrum, J.; Müller,J. and Ay, N.: Invariance properties of the natural gradient in overparametrised systems in Information Geometry (2022) [DOI]
  • Langer, C. and Ay, N.: How Morphological Computation Shapes Integrated Information in Embodied Agents. frontiers in Psychology | Cognition (2021) [DOI]
  • Tirnakli, U.; Tsallis, C. and Ay, N.: Approaching a large deviation theory for complex systems. Nonlinear Dyn (2021) [DOI]
  • Felice, D. and Ay, N.: Towards a canonical divergence within information geometry. Information Geometry, 4 , pp. 65–130 (2021) [DOI]
  • Ay, N.: Confounding Ghost Channels and Causality : A New Approach to Causal Information Flows. Vietnam Journal of Mathematics (2021) [DOI]
  • Felice, D. and N. Ay: Towards a canonical divergence within information geometry. Information geometry, Vol. not yet known, pp. not yet known MIS-Preprint: 43/2018[DOI][ARXIV]
  • Ay, N.: On the locality of the natural gradient for learning in deep Bayesian networks. Information geometry, Vol. not yet known, pp. not yet known MIS-Preprint: 59/2020[DOI][ARXIV]
  • Ay, N.: Ingredients for robustness. Theory in biosciences, 139 (2020) 4, p. 309-318 [DOI]
  • Ay, N. ; Polani, D. and N. Virgo: Information decomposition based on cooperative game theory. Kybernetika, 56 (2020) 5, p. 979-1014 MIS-Preprint: 81/2020[DOI][ARXIV]
  • Ay, N. and M. Studeny: Special issue in memory of František Matúš : editorial. Kybernetika, 56 (2020) 5, p. 843-849[FREELINK]
  • Krakauer, D. C. ; Bertschinger, N. ; Olbrich, E. ; Flack, J. C. and N. Ay: The information theory of individuality. Theory in biosciences, 139 (2020) 2, p. 209-223 [DOI][ARXIV][FREELINK]
  • Langer, C. and N. Ay: Complexity as causal information integration. Entropy, 22 (2020) 10, 1107 MIS-Preprint: 85/2020[DOI][ARXIV]
  • Felice, D. and N. Ay: Canonical divergence for flat \(\alpha\)-connections : classical and quantum. Entropy, 21 (2019) 9, 831 [DOI][ARXIV]
  • Felice, D. ; Mancini, S. and N. Ay: Canonical divergence for measuring classical and quantum complexity. Entropy, 21 (2019) 4, 435 [DOI][ARXIV]
  • Ay, N. ; Jost, J. ; Lê, H. V. and L. J. Schwachhöfer: Parametrized measure models. Bernoulli, 24 (2018) 3, p. 1692-1725 MIS-Preprint: 69/2015[DOI][ARXIV]
  • Felice, D. and N. Ay: Dynamical systems induced by canonical divergence in dually flat manifolds. Information geometry, Vol. not yet known, pp. not yet known MIS-Preprint: 103/2018[ARXIV]
  • Ghazi-Zahedi, K. ; Langer, C. and N. Ay: Morphological computation : synergy of body and brain. Entropy, 19 (2017) 9, 456 [DOI]
  • Kanwal, M. S. ; Grochow, J. A. and N. Ay: Comparing information-theoretic measures of complexity in Boltzmann machines. Entropy, 19 (2017) 7, 310 [DOI][ARXIV]
  • Ghazi-Zahedi, K. ; Haeufle, D. F. B. ; Montúfar, G. ; Schmitt, S. and N. Ay: Evaluating morphological computation in muscle and DC-motor driven models of hopping movements. Frontiers in robotics and AI, 3 (2016), 42 [DOI][ARXIV]
  • Perrone, P. and N. Ay: Hierarchical quantification of synergy in channels. Frontiers in robotics and AI, 2 (2016), 35 MIS-Preprint: 86/2015[DOI][ARXIV]
  • Pfante, O. ; Bertschinger, N. ; Olbrich, E. ; Ay, N. and J. Jost: Wie findet man eine geeignete Beschreibungsebene für ein komplexes System?. Jahrbuch der Max-Planck-Gesellschaft, 2016 (2016), Forschungsbericht – Max-Planck-Institut für Mathematik in den Naturwissenschaften[FREELINK]
  • Sato, Y. and N. Ay: Information flow in learning a coin-tossing game. Nonlinear theory and its applications, 7 (2016) 2, p. 118-125 [DOI]
  • Ay, N.: Information geometry on complexity and stochastic interaction. Entropy, 17 (2015) 4, p. 2432-2458 MIS-Preprint: 95/2001[DOI]
  • Ay, N.: Geometric design principles for brains of embodied agents. Künstliche Intelligenz : KI, 29 (2015) 4, p. 389-399 [DOI]
  • Ay, N. and S. Amari: A novel approach to canonical divergences within information geometry. Entropy, 17 (2015) 12, p. 8111-8129 MIS-Preprint: 73/2015[DOI]
  • Ay, N. ; Jost, J. ; Lê, H. V. and L. J. Schwachhöfer: Information geometry and sufficient statistics. Probability theory and related fields, 162 (2015) 1-2, p. 327-364 MIS-Preprint: 65/2012[DOI][ARXIV]
  • Ay, N. and W. Löhr: The Umwelt of an embodied agent : a measure-theoretic definition. Theory in biosciences, 134 (2015) 3-4, p. 105-116 MIS-Preprint: 74/2015[DOI][ARXIV]
  • Montúfar, G. ; Ay, N. and K. Ghazi-Zahedi: Geometry and expressive power of conditional restricted Boltzmann machines. Journal of machine learning research, 16 (2015), p. 2405-2436 MIS-Preprint: 16/2014[ARXIV][FREELINK]
  • Montúfar, G. ; Ghazi-Zahedi, K. and N. Ay: A theory of cheap control in embodied systems. PLoS computational biology, 11 (2015) 9, e1004427 MIS-Preprint: 70/2014[DOI][ARXIV]
  • Pfante, O. and N. Ay: Operator-theoretic identification of closed sub-systems of dynamical systems. An interdisciplinary journal of discontinuity, nonlinearity, and complexity, 4 (2015) 1, p. 91-109 MIS-Preprint: 4/2015[DOI]
  • Salge, C. ; Ay, N. ; Polani, D. and M. Prokopenko: Zipf’s law : balancing signal usage cost and communication efficiency. PLOS ONE, 10 (2015) 10, e0139475 [DOI][FREELINK]
  • Steudel, B. and N. Ay: Information-theoretic inference of common ancestors. Entropy, 17 (2015) 4, p. 2304-2327 [DOI][ARXIV]
  • Weis, S. ; Knauf, A. ; Ay, N. and M.-J. Zhao: Maximizing the divergence from a hierarchical model of quantum states. Open systems and information dynamics, 22 (2015) 1, 1550006 MIS-Preprint: 58/2014[DOI][ARXIV]
  • Bertschinger, N. ; Rauh, J. ; Olbrich, E. ; Jost, J. and N. Ay: Quantifying unique information. Entropy, 16 (2014) 4, p. 2161-2183 MIS-Preprint: 102/2013[DOI][ARXIV][CODELINK]
  • Montúfar, G. ; Rauh, J. and N. Ay: On the Fisher metric of conditional probability polytopes. Entropy, 16 (2014) 6, p. 3207-3233 MIS-Preprint: 87/2014[DOI][ARXIV]
  • Moritz, P. ; Reichardt, J. and N. Ay: Discriminating between causal structures in Bayesian networks given partial observations. Kybernetika, 50 (2014) 2, p. 284-295 [DOI]
  • Pfante, O. ; Bertschinger, N. ; Olbrich, E. ; Ay, N. and J. Jost: Comparison between different methods of level identification. Advances in complex systems, 17 (2014) 2, 1450007 [DOI]
  • Pfante, O. ; Olbrich, E. ; Bertschinger, N. ; Ay, N. and J. Jost: Closure measures for coarse-graining of the tent map. Chaos, 24 (2014), 013136 MIS-Preprint: 108/2013[DOI]
  • Rauh, J. and N. Ay: Robustness, canalyzing functions and systems design. Theory in biosciences, 133 (2014) 2, p. 63-78 MIS-Preprint: 66/2012[DOI][ARXIV]
  • Ghazi-Zahedi, K. and N. Ay: Quantifying morphological computation. Entropy, 15 (2013) 5, p. 1887-1915 MIS-Preprint: 11/2013[DOI][ARXIV]
  • Ghazi-Zahedi, K. ; Martius, G. and N. Ay: Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting : a critical analysis. Frontiers in psychology, 4 (2013), 801 MIS-Preprint: 60/2013[DOI][ARXIV]
  • Lohmann, G. ; Stelzer, J. ; Neumann, J. ; Ay, N. and R. Turner: ‘More is different’ in functional magnetic resonance imaging : a review of recent data analysis techniques. Brain Connectivity, 3 (2013) 3, p. 223-239 [DOI]
  • Martius, G. ; Der, R. and N. Ay: Information driven self-organization of complex robotic behaviors. PLOS ONE, 8 (2013) 5, e63400 MIS-Preprint: 15/2013[DOI][ARXIV]
  • Ay, N. ; Bernigau, H. ; Der, R. and M. Prokopenko: Information-driven self-organization : the dynamical system approach to autonomous robot behavior. Theory in biosciences, 131 (2012) 3, p. 161-179 [DOI]
  • Ay, N. ; Der, R. and M. Prokopenko: Guided self-organization : perception-action loops of embodied systems. Theory in biosciences, 131 (2012) 3, p. 125-127 [DOI]
  • Ay, N. and W. Wenzel: On solution sets of information inequalities. Kybernetika, 48 (2012) 5, p. 845-864 MIS-Preprint: 16/2011[FREELINK]
  • Löhr, W. ; Szkoła, A. and N. Ay: Process dimension of classical and non-commutative processes. Open systems and information dynamics, 19 (2012) 1, 1250007 MIS-Preprint: 52/2011[DOI][ARXIV]
  • Ay, N. ; Müller, M. and A. Szkoła: Effective complexity of stationary process realizations. Entropy, 13 (2011) 6, p. 1200-1211 MIS-Preprint: 2/2010[DOI][ARXIV]
  • Ay, N. ; Olbrich, E. ; Bertschinger, N. and J. Jost: A geometric approach to complexity. Chaos, 21 (2011) 3, 037103 MIS-Preprint: 53/2011[DOI]
  • Montúfar, G. and N. Ay: Refinements of universal approximation results for deep belief networks and restricted Boltzmann machines. Neural computation, 23 (2011) 5, p. 1306-1319 MIS-Preprint: 23/2010[DOI][ARXIV]
  • Rauh, J. ; Kahle, T. and N. Ay: Support sets in exponential families and oriented matroid theory. International journal of approximate reasoning, 52 (2011) 5, p. 613-626 MIS-Preprint: 28/2009[DOI][ARXIV]
  • Ay, N. ; Müller, M. and A. Szkoła: Effective complexity and its relation to logical depth. IEEE transactions on information theory, 56 (2010) 9, p. 4593-4607 [DOI][ARXIV]
  • Ghazi-Zahedi, K. ; Ay, N. and R. Der: Higher coordination with less control : a result of information maximization in the sensorimotor loop. Adaptive behavior, 18 (2010) 3/4, p. 338-355 [DOI][ARXIV]
  • Olbrich, E. ; Kahle, T. ; Bertschinger, N. ; Ay, N. and J. Jost: Quantifying structure in networks. The European physical journal / B, 77 (2010) 2, p. 239-247 MIS-Preprint: 81/2009[DOI][ARXIV]
  • Prokopenko, M. ; Ay, N. ; Obst, O. and D. Polani: Phase transitions in least-effort communications. Journal of statistical mechanics, 2010 (2010) 11, P11025 [DOI]
  • Ay, N.: A refinement of the common cause principle. Discrete applied mathematics, 157 (2009) 10, p. 2439-2457 [DOI]
  • Kahle, T. ; Olbrich, E. ; Jost, J. and N. Ay: Complexity measures from interaction structures. Physical review / E, 79 (2009) 2, pt. 2, 026201 MIS-Preprint: 44/2008[DOI][ARXIV]
  • Kahle, T. ; Wenzel, W. and N. Ay: Hierarchical models, marginal polytopes, and linear codes. Kybernetika, 45 (2009) 2, p. 189-207 MIS-Preprint: 30/2008[ARXIV][FREELINK]
  • Löhr, W. and N. Ay: On the generative nature of prediction. Advances in complex systems, 12 (2009) 2, p. 169-194 MIS-Preprint: 8/2008[DOI]
  • Ay, N. ; Bertschinger, N. ; Der, R. ; Güttler, F. and E. Olbrich: Predictive information and explorative behavior of autonomous robots. The European physical journal / B, 63 (2008) 3, p. 329-339 [DOI]
  • Ay, N. and D. Polani: Information flows in causal networks. Advances in complex systems, 11 (2008) 1, p. 17-41 MIS-Preprint: 47/2006[DOI]
  • Bertschinger, N. ; Olbrich, E. ; Ay, N. and J. Jost: Autonomy : an information-theoretic perspective. Biosystems, 91 (2008) 2, p. 331-345 [DOI]
  • Olbrich, E. ; Bertschinger, N. ; Ay, N. and J. Jost: How should complexity scale with system size?. The European physical journal / B, 63 (2008) 3, p. 407-415 [DOI]
  • Ay, N. ; Flack, J. C. and D. C. Krakauer: Robustness and complexity co-constructed in multimodal signalling networks. Philosophical transactions of the Royal Society of London / B, 362 (2007) 1479, p. 441-447 [DOI]
  • Ay, N. and D. C. Krakauer: Geometric robustness theory and biological networks. Theory in biosciences, 125 (2007) 2, p. 93-121 MIS-Preprint: 14/2006[DOI]
  • Jost, J. ; Bertschinger, N. ; Olbrich, E. ; Ay, N. and S. Frankel: An information theoretic approach to system differentiation on the basis of statistical dependencies between subsystems. Physica / A, 378 (2007) 1, p. 1-10 [DOI]
  • Wennekers, T. ; Ay, N. and P. Andras: High-resolution multiple-unit EEG in cat auditory cortex reveals large spatio-temporal stochastic interactions. Biosystems, 89 (2007) 1/3, p. 190-197 [DOI]
  • Ay, N. and A. Knauf: Maximizing multi-information. Kybernetika, 42 (2006) 5, p. 517-538 MIS-Preprint: 42/2003[ARXIV]
  • Wennekers, T. and N. Ay: A temporal learning rule in recurrent systems supports high spatio-temporal stochastic interactions. Neurocomputing, 69 (2006) 10/12, p. 1199-1202 [DOI]
  • Ay, N. and I. Erb: On a notion of linear replicator equations. Journal of dynamics and differential equations, 17 (2005) 2, p. 427-451 [DOI]
  • Wennekers, T. and N. Ay: Finite state automata resulting from temporal information maximization and a temporal learning rule. Neural computation, 17 (2005) 10, p. 2258-2290 [DOI]
  • Wennekers, T. and N. Ay: Stochastic interaction in associative nets. Neurocomputing, 65 (2005), p. 387-392 [DOI]
  • Erb, I. and N. Ay: Multi-information in the thermodynamic limit. Journal of statistical physics, 115 (2004) 3-4, p. 949-976 MIS-Preprint: 58/2003[DOI]
  • Ay, N. and W. Tuschmann: Duality versus dual flatness in quantum information geometry. Journal of mathematical physics, 44 (2003) 4, p. 1512-1518 MIS-Preprint: 69/2002[DOI]
  • Ay, N. and T. Wennekers: Temporal infomax leads to almost deterministic dynamical systems. Neurocomputing, 52 (2003) 4, p. 461-466 [DOI]
  • Ay, N. and T. Wennekers: Dynamical properties of strongly interacting Markov chains. Neural networks, 16 (2003) 10, p. 1483-1497 MIS-Preprint: 107/2001[DOI]
  • Wennekers, T. and N. Ay: Spatial and temporal stochastic interaction in neuronal assemblies. Theory in biosciences, 122 (2003) 1, p. 5-18 [DOI]
  • Wennekers, T. and N. Ay: Temporal Infomax on Markov chains with input leads to finite state automata. Neurocomputing, 52 (2003) 4, p. 431-436 [DOI]
  • Ay, N.: Locality of global stochastic interaction in directed acyclic networks. Neural computation, 14 (2002) 12, p. 2959-2980 MIS-Preprint: 54/2001[DOI]
  • Ay, N.: An information-geometric approach to a theory of pragmatic structuring. The annals of probability, 30 (2002) 1, p. 416-436 MIS-Preprint: 52/2000[FREELINK]
  • Ay, N. and W. Tuschmann: Dually flat manifolds and global information geometry. Open systems and information dynamics, 9 (2002) 2, p. 195-200 MIS-Preprint: 24/2002[DOI]
  • Wenzel, W. ; Ay, N. and F. Pasemann: Hyperplane arrangements separating arbitrary vertex classes in \(\mathscr n\)-cubes. Advances in applied mathematics, 25 (2000) 3, p. 284-306 MIS-Preprint: 35/1999[DOI]

Publications in Books and Conference Proceedings

  • Erb, I. and N. Ay: The information-geometric perspective of compositional data analysis. Advances in compositional data analysis : Festschrift in Honour of Vera Pawlowsky-Glahn / P. Filzmoser… (eds.). Springer, 2021. – P. 21-43 [DOI][ARXIV]
  • Carlini, L. ; Ay, N. and C. Görgen: A numerical effciency analysis of a common ancestor condition. Mathematical aspects of computer and information sciences : 8th international conference, MACIS 2019, Gebze-Istanbul, Turkey, November 13-15, 2019 ; revised selected papers / D. Slamanig… (eds.). Springer, 2020. – P. 357-363 (Lecture notes in computer science ; 11989) [DOI][FREELINK]
  • Ay, N. ; Rauh, J. and G. Montúfar: A continuity result for optimal memoryless planning in POMDPs. RLDM 2019 : 4th multidisciplinary conference on reinforcement learning and decision making ; July 7-10, 2019 ; Montréal, Canada University, 2019. – P. 362-365 MIS-Preprint: 5/2021[FREELINK]
  • Felice, D. and N. Ay: Divergence functions in information geometry. Geometric science of information : 4th international conference, GSI 2019, Toulouse, France, August 27-29, 2019, proceedings / F. Nielsen… (eds.). Springer, 2019. – P. 433-442 (Lecture notes in computer science ; 11712) [DOI][ARXIV]
  • Montúfar, G. ; Rauh, J. and N. Ay: Task-agnostic constraining in average reward POMDPs. Task-agnostic reinforcement learning : workshop at ICLR, 06 May 2019, New Orleans ICLR, 2019 MIS-Preprint: 9/2021[FREELINK]
  • Ghazi-Zahedi, K. ; Langer, C. and N. Ay: Morphological computation : synergy of body and brain [Entropy, 19 (2017) 9, 456]. Information decomposition of target effects from multi-source interactions : [collected articles from the special issue published in Entropy] / J. T. Lizier… (eds.). MDPI, 2018. – P. 267-281 [DOI]
  • Langer, C. and N. Ay: Comparison and connection between the joint and the conditional generalized iterative scaling algorithm. Proceedings of the 11th workshop on uncertainty processing WUPES ’18, June 6-9, 2018 / V. Kratochvíl (ed.). MatfyzPress, 2018. – P. 105-116[FREELINK]
  • Montúfar, G. ; Rauh, J. and N. Ay: Uncertainty and stochasticity of optimal policies. Proceedings of the 11th workshop on uncertainty processing WUPES ’18, June 6-9, 2018 / V. Kratochvíl (ed.). MatfyzPress, 2018. – P. 133-140 MIS-Preprint: 8/2021[FREELINK]
  • Schwachhöfer, L. J. ; Ay, N. ; Jost, J. and H. V. Lê: Congruent families and invariant tensors. Information geometry and its applications : on the occasion of Shun-ichi Amari’s 80th Birthday, IGAIA IV Liblice, Czech Republic, June 2016 / N. Ay… (eds.). Springer, 2018. – P. 157-187 (Springer proceedings in mathematics and statistics ; 252) [DOI][ARXIV]
  • Ay, N. ; Jost, J. ; Lê, H. V. and L. J. Schwachhöfer: Parametrized measure models. Information geometry / N. Ay Springer, 2017. – P. 121-184 (Ergebnisse der Mathematik und ihrer Grenzgebiete. 3. Folge / A series of modern surveys in mathematics ; 64) MIS-Preprint: 69/2015[DOI][ARXIV]
  • Montúfar, G. ; Ghazi-Zahedi, K. and N. Ay: Stochasticity of optimal policies for POMDPs. RLDM 2017 : 3rd multidisciplinary conference on reinforcement learning and decision making ; June 11-14, 2017 ; Ann Arbor, Michigan, USA University, 2017[FREELINK]
  • Schwachhöfer, L. J. ; Ay, N. ; Jost, J. and H. V. Lê: Parametrized measure models and a generalization of Chentsov’s theorem. International conference on information geometry and its applications IV : Liblice, June 12-17, 2016 ; in honor of Shun-ichi Amari / N. Ay… (eds.). Matfyzpress, 2016. – P. 17-17[FREELINK]
  • Amari, S. and N. Ay: Standard divergence in manifold of dual affine connections. Geometric science of information : second international conference, GSI 2015, Palaiseau, France, October 28-30, 2015, proceedings / F. Nielsen… (eds.). Springer, 2015. – P. 320-325 (Lecture notes in computer science ; 9389) [DOI]
  • Perrone, P. and N. Ay: Decomposition of Markov kernels. Proceedings of the 10th workshop on uncertainty processing WUPES ’15, Moninec, Czech Republic, September 16-19, 2015 / V. Kratochvíl (ed.). Oeconomica, 2015. – P. 167-178[FREELINK]
  • Schwachhöfer, L. J. ; Ay, N. ; Jost, J. and H. V. Lê: Invariant geometric structures on statistical models. Geometric science of information : second international conference, GSI 2015, Palaiseau, France, October 28-30, 2015, proceedings / F. Nielsen… (eds.). Springer, 2015. – P. 150-158 (Lecture notes in computer science ; 9389) [DOI]
  • Ay, N. and K. Ghazi-Zahedi: On the causal structure of the sensorimotor loop. Guided self-organization : inception / M. Prokopenko (ed.). Springer, 2014. – P. 261-294 (Emergence, complexity, and computation) [DOI]
  • Prokopenko, M. ; Polani, D. and N. Ay: On the cross-disciplinary nature of guided self-organisation. Guided self-organization : inception / M. Prokopenko (ed.). Springer, 2014. – P. 3-15 (Emergence, complexity, and computation) [DOI]
  • Ay, N. and K. Ghazi-Zahedi: Causal effects for prediction and deliberative decision making of embodied systems. Advances in cognitive neurodynamics III : proceedings of the 3rd International Conference on Cognitive Neurodynamics 2011 ; [June 9-13, 2011, Hilton Niseko Village, Hokkaido, Japan] / Y. Yamaguchi (ed.). Springer, 2013. – P. 499-506 (Advances in cognitive neurodynamics) MIS-Preprint: 22/2011[DOI]
  • Ay, N. ; Montúfar, G. and J. Rauh: Selection criteria for neuromanifolds of stochastic dynamics. Advances in cognitive neurodynamics III : proceedings of the 3rd International Conference on Cognitive Neurodynamics 2011 ; [June 9-13, 2011, Hilton Niseko Village, Hokkaido, Japan] / Y. Yamaguchi (ed.). Springer, 2013. – P. 147-154 (Advances in cognitive neurodynamics) MIS-Preprint: 15/2011[DOI]
  • Montúfar, G. ; Rauh, J. and N. Ay: Maximal information divergence from statistical models defined by neural networks. Geometric science of information : first international conference, GSI 2013, Paris, France, August 28-30, 2013. Proceedings / F. Nielsen… (eds.). Springer, 2013. – P. 759-766 (Lecture notes in computer science ; 8085) MIS-Preprint: 31/2013[DOI][ARXIV]
  • Moritz, P. ; Reichardt, J. and N. Ay: A new common cause principle for bayesian networks. Proceedings of the 9th workshop on uncertainty processing WUPES ’12 : Marianske Lazne, Czech Republik ; 12-15th September 2012 Academy of Sciences of the Czech Republik / Institute of Information Theory and Automation, 2012. – P. 149-162[FREELINK]
  • Montúfar, G. ; Rauh, J. and N. Ay: Expressive power and approximation errors of restricted Boltzmann machines. Advances in neural information processing systems 24 : 25th annual conference on neural information processing systems 2011, Granada, Spain December 12th – 15th ; NIPS 2011 / J. Shawe-Taylor (ed.). Neural Information Processing Systems, 2011. – P. 415-423 MIS-Preprint: 27/2011[ARXIV][FREELINK]
  • Krakauer, D. C. ; Flack, J. C. and N. Ay: Probabilistic design principles for robust multimodal communication networks. Modelling perception with artificial neural networks / C. R. Tosh… (eds.). Cambridge University Press, 2010. – P. 255-268 [DOI]
  • Löhr, W. and N. Ay: Non-sufficient memories that are sufficient for prediction. Complex sciences : first international conference, Complex 2009, Shanghai, China, February 23 – 25, 2009, revised papers. Pt. 1 / J. Zhou (ed.). Springer, 2009. – P. 265-276 (Lecture notes of the Institute for Computer Science, Social Informatics and Telecommunications Engineering ; 4) [DOI]
  • Der, R. ; Güttler, F. and N. Ay: Predictive information and emergent cooperativity in a chain of mobile robots. Artificial Life XI : Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems MIT Press, 2008. – P. 166-172
  • Ay, N. ; Olbrich, E. ; Bertschinger, N. and J. Jost: A unifying framework for complexity measures of finite systems. ECCS’06 : proceedings of the European Conference on Complex Systems 2006 ; towards a science of complex systems / J. Jost… (eds.). European Complex Systems Society, 2006. – P. 80-80[FREELINK]
  • Bertschinger, N. ; Olbrich, E. ; Ay, N. and J. Jost: Autonomy : an information theoretic perspective. Artificial life X : proceedings of the tenth international conference on the synthesis and simulation of living systems / L. M. Rocha… (eds.). MIT Press, 2006. – P. 7-12
  • Bertschinger, N. ; Olbrich, E. ; Ay, N. and J. Jost: Information and closure in systems theory. Explorations in the complexity of possible life : abstracting and synthesizing the principles of living systems ; proceedings of the 7th German Workshop on Artificial Life, July 26 – 28, 2006, Jena, Germany / S. Artmann… (eds.). IOS Press, 2006. – P. 9-19
  • Kahle, T. and N. Ay: Support sets of distributions with given interaction structure. 7th Workshop on Uncertainty Processing : WUPES’06 ; Mikulov, Czech Republik ; 16-20th September 2006 Academy of Sciences of the Czech Republik / Institute of Information Theory and Automation, 2006. – P. 52-61 MIS-Preprint: 94/2006[FREELINK]
  • Matúš, F. and N. Ay: On maximization of the information divergence from an exponential family. Proceedings of 6th workshop on uncertainty processing : Hejnice, September 24-27, 2003 Oeconomica, 2003. – P. 199-204 MIS-Preprint: 46/2003

Preprints

  • Montúfar, G. and Rauh, J. and Ay, N.: Uncertainty and Stochasticity of Optimal Policies. MIS-Preprint: 8/2021
  • Rauh, J. and., Ay, N. and Montúfar, G.: A continuity result for optimal memoryless planning in POMDPs. MIS-Preprint: 5/2021
  • Montúfar, G. and Rauh, J. and Ay, N.: Task-agnostic constraining in average reward POMDPs. MIS-Preprint: 9/2021
  • Langer, C. and N. Ay: Apportionment of work among environment, body and brain of an agent. MIS-Preprint: 2/2021
  • Ay, N.: Confounding ghost channels and causality : a new approach to causal information flows. MIS-Preprint: 75/2020[ARXIV]
  • Ay, N. ; Bertschinger, N. ; Jost, J. ; Olbrich, E. and J. Rauh: Information and complexity, or: Where is the information?. MIS-Preprint: 102/2020
  • Tirnakli, U. ; Tsallis, C. and N. Ay: Approaching a large deviation theory for complex systems. [ARXIV]
  • Várady, C. ; Volpi, R. ; Malagò, L. and N. Ay: Natural reweighted wake-sleep. [FREELINK]
  • Várady, C. ; Volpi, R. ; Malagò, L. and N. Ay: Natural wake-sleep algorithm. MIS-Preprint: 84/2020[ARXIV]
  • Montúfar, G. ; Ghazi-Zahedi, K. and N. Ay: Information theoretically aided reinforcement learning for embodied agents. [ARXIV]
  • Perrone, P. and N. Ay: Iterative scaling algorithm for channels. [ARXIV]
  • Montúfar, G. ; Ghazi-Zahedi, K. and N. Ay: Geometry and determinism of optimal stationary control in partially observable Markov decision processes. MIS-Preprint: 22/2016[ARXIV]
  • Ay, N. and W. Löhr: A measure-theoretic description of the intrinsic view of embodied agents. [FREELINK]
  • Ay, N. ; Jost, J. ; Lê, H. V. and L. J. Schwachhöfer: A characterization of the Fisher metric and the Amari-Chentsov tensor in information geometry.
  • Rauh, J. and N. Ay: Robustness and conditional independence ideals. MIS-Preprint: 63/2011[ARXIV]
  • Ay, N. and G. Struck: Stochastic independence of crosstalk variables in the hopfield model. MIS-Preprint: 65/2006
  • Sato, Y. and N. Ay: Adaptive dynamics for interacting Markovian processes. [ARXIV]
  • Wennekers, T. and N. Ay: Information-theoretic grounding of finite automata in neural systems. MIS-Preprint: 52/2002

Academic Theses

  • Ay, N.: Aspekte einer Theorie pragmatischer Informationsstrukturierung. Dissertation, Universität Leipzig, 2001

Articles in Preparation (Preliminary Titles)

  • Ay, N. ; Gibilisco, P. and F. Matúš (eds.): Information geometry and its applications : on the occasion of Shun-ichi Amari’s 80th Birthday, IGAIA IV Liblice, Czech Republic, June 2016. Springer, 2018. – X, 456 p. (Springer proceedings in mathematics and statistics ; 252) ISBN 978-3-319-97797-3 [DOI]
  • Ay, N. ; Krakauer, D. C. and J. C. Flack: Robustness, causal networks, and experimental design. Princeton University Press, 2018
  • Ay, N. ; Jost, J. ; Lê, H. V. and L. J. Schwachhöfer: Information geometry. Springer, 2017. – XI, 407 p. (Ergebnisse der Mathematik und ihrer Grenzgebiete. 3. Folge / A series of modern surveys in mathematics ; 64) ISBN 978-3-319-56477-7 [DOI]

Reports

  • N. Ay. Principles of Robustness
    (in German). Annual Report of the Max Planck Society (2006). N. Ay, T. Wennekers. Complexity of Cognitive Systems
    (in German). Annual Report of the Max Planck Society (2003).

Media and Popular Science (refers to work with Ralf Der)

  • Virtual creatures and robots take on `a life of their own’.
    Telegraph (London) August 11, 2008 by Roger Highfield.
  • Robots learn to move themselves.
    BBC News August 6, 2008 by Jason Palmer.
  • Künstliches Leben: Roboter ringen im Rechner.
    Tagesanzeiger (Zürich).
  • Roboter werden aus Erfahrung klug.
    Die Welt (Hamburg).
  • Roboter entfalten mit einem Mathemodell Eigenleben.
    Computer Zeitung Online.
  • Roboter entfalten ein Eigenleben.
    Pressemitteilung der Max-Planck-Gesellschaft (MPG, München).
  • TV: Eigensinnige Roboter.
    3sat (Newton, 2008).
  • Die Klugheit der Dinge.
    Max-Planck-Forschung, Wissenschaftsmagazin der MPG, Heft 1, 2009.
  • Die Klugheit der Dinge.
    Wissenschaftsvideo der MPG 2009, to appear.
  • Selbstbestimmte künstliche Wesen.
    Spektrum der Wissenschaft, to appear in February 2010.
  • Eine Maschine wird Mensch.
    FOCUS Nr. 27, 2009.
  • Spielplatz der Roboter.
    Berliner Zeitung, September 5, 2009.

Scroll to Top