Working Papers/Reports

 

Lower-level publication types

Recent Submissions 

  1. Neuromorphic Visual Scene Understanding with Resonator Networks 

    Renner, Alpha; Supic, Lazar; Danielescu, Andreea; et al. (2022)
    Inferring the position of objects and their rigid transformations is still an open problem in visual scene understanding. Here we propose a neuromorphic solution that utilizes an efficient factorization network based on three key concepts: (1) a computational framework based on Vector Symbolic Architectures (VSA) with complex-valued vectors; (2) the design of Hierarchical Resonator Networks (HRN) to deal with the non-commutative nature ...
    Working Paper

  2. Goal-directed vocal planning in a songbird 

    Zai, Anja T.; Stepien, Anna E.; Cavé-Lopez, Sophie; et al. (2022)
    Working Paper

  3. Multimodal system for recording individual-level behaviors in songbird groups 

    Rüttimann, L.; Rychen, J.; Tomka, T.; et al. (2022)
    Working Paper

  4. Biologically-Inspired Continual Learning of Human Motion Sequences 

    Ott, Joachim; Liu, Shih-Chii (2022)
    This work proposes a model for continual learning on tasks involving temporal sequences, specifically, human motions. It improves on a recently proposed brain-inspired replay model (BI-R) by building a biologically-inspired conditional temporal variational autoencoder (BI-CTVAE), which instantiates a latent mixture-of-Gaussians for class representation. We investigate a novel continual-learning-to-generate (CL2Gen) scenario where the model ...
    Working Paper

  5. Learning the action inventory of a complex skill via an intrinsic reward 

    Toutounji, H; Zai, A; Tchernichovski, O; et al. (2022)
    Working Paper

  6. Full-duplex acoustic interaction system for cognitive experiments with cetaceans 

    Rychen, Jörg; Semoroz, Julie; Eckerle, Alexander; et al. (2022)
    Working Paper

  8. Vold-Kalman Filter Order tracking of Axle Box Accelerations for Railway Stiffness Assessment 

    Hoelzl, Cyprien; Dertimanis, Vasilis; Ancu, Lucian; et al. (2022)
    arXiv
    Intelligent data-driven monitoring procedures hold enormous potential for ensuring safe operation and optimal management of the railway infrastructure in the face of increasing demands on cost and efficiency. Numerous studies have shown that the track stiffness is one of the main parameters influencing the evolution of degradation that drives maintenance processes. As such, the measurement of track stiffness is fundamental for characterizing ...
    Working Paper

  9. Does international “offshoring” of environmental impacts reflect consumer NIMBYism? 

    Presberger, David; Kolcava, Dennis; Bernauer, Thomas (2022)
    Working Paper

  10. High-Dimensional Inference in Bayesian Networks 

    Bayer, Fritz M.; Moffa, Giusi; Beerenwinkel, Niko; et al. (2021)
    Inference of the marginal probability distribution is defined as the calculation of the probability of a subset of the variables and is relevant for handling missing data and hidden variables. While inference of the marginal probability distribution is crucial for various problems in machine learning and statistics, its exact computation is generally not feasible for categorical variables in Bayesian networks due to the NP-hardness of ...
    Working Paper

  11. Deep exponential families for single-cell data analysis 

    Ferreira, Pedro F.; Kuipers, Jack; Beerenwinkel, Niko (2022)
    Working Paper

  12. Joint copy number and mutation phylogeny reconstruction from single-cell amplicon sequencing data 

    Sollier, Etienne; Kuipers, Jack; Takahashi, Koichi; et al. (2022)
    Working Paper

  13. Practical and scalable simulations of non-Markovian stochastic processes 

    Pelissier, Aurelien; Phan, Miroslav; Beerenwinkel, Niko; et al. (2022)
    Discrete stochastic processes are widespread in natural systems with many applications across physics, biochemistry, epidemiology, sociology, and finance. While analytic solutions often cannot be derived, existing simulation frameworks can generate stochastic trajectories compatible with the dynamical laws underlying the random phenomena. However, most simulation algorithms assume the system dynamics are memoryless (Markovian assumption), ...
    Working Paper

  15. Tracking SARS-CoV-2 genomic variants in wastewater sequencing data with<i>LolliPop</i> 

    Dreifuss, David; Topolsky, Ivan; Icer Baykal, Pelin; et al. (2022)
    Working Paper

  16. Bayesian structure learning and sampling of Bayesian networks with the R package BiDAG 

    Suter, Polina; Kuipers, Jack; Moffa, Giusi; et al. (2021)
    The R package BiDAG implements Markov chain Monte Carlo (MCMC) methods for structure learning and sampling of Bayesian networks. The package includes tools to search for a maximum a posteriori (MAP) graph and to sample graphs from the posterior distribution given the data. A new hybrid approach to structure learning enables inference in large graphs. In the first step, we define a reduced search space by means of the PC algorithm or based ...
    Working Paper

  17. Linear isoperimetric inequality for homogeneous Hadamard manifolds 

    Isleifsson, Hjalti (2022)
    arXiv
    Working Paper

  18. A synthetic bispecific antibody capable of neutralizing SARS-CoV-2 Delta and Omicron 

    Yuan, Tom Z.; Lucas, Carolina; Monteiro, Valter S.; et al. (2022)
    Working Paper

  20. A combinatorial higher-rank hyperbolicity condition 

    Lang, Urs; Jørgensen, Martina (2022)
    arXiv
    Working Paper

View more