Blar i ODA Open Digital Archive på forfatter "Nichele, Stefano"

Viser treff 1-20 av 40

    • Achieving Connectivity between Wide Areas Through Self-Organising Robot Swarms using Embodied Evolution 

      Erik Aaron, Hansen; Nichele, Stefano; Yazidi, Anis; Haugerud, Hårek; Abolpour Mofrad, Asieh; Alcocer, Alex (Chapter; Peer reviewed, 2018)
      Abruptions to the communication infrastructuremight occur occasionally, where manual intervention by dedi-cated personnel is needed to fix the interruptions, restoring com-munication abilities. However, sometimes this can ...

    • Activity dependent delay learning in spiking neural networks 

      Farner, Jørgen (ACIT;2022, Master thesis, 2022)
      Several observations indicate activity dependent changes in the propagation velocity of action potentials in biological neural networks. These changes are believed to be deliberate mechanisms in the brain used to mediate ...

    • Assessing the robustness of critical behavior in stochastic cellular automata 

      Pontes Filho, Sidney; Lind, Pedro; Nichele, Stefano (Physica D : Non-linear phenomena;Volume 441, December 2022, 133507, Peer reviewed; Journal article, 2022-09-13)
      There is evidence that biological systems, such as the brain, work at a critical regime robust to noise, and are therefore able to remain in it under perturbations. In this work, we address the question of robustness of ...

    • Assessment and manipulation of the computational capacity of in vitro neuronal networks through criticality in neuronal avalanches 

      Heiney, Kristine; Huse Ramstad, Ola; Sandvig, Ioanna; Sandvig, Axel; Nichele, Stefano (2019 IEEE Symposium Series on Computational Intelligence (SSCI);, Conference object, 2020)
      In this work, we report the preliminary analysis of the electrophysiological behavior of in vitro neuronal networks to identify when the networks are in a critical state based on the size distribution of network-wide ...

    • Autonomous configuration of network parameters in operating systems using evolutionary algorithms 

      Gembala, Bartosz Gembala; Yazidi, Anis; Haugerud, Hårek; Nichele, Stefano (Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems;, Chapter; Peer reviewed, 2018)
      By default, the Linux network stack is not configured for highspeed large file transfer. The reason behind this is to save memory resources. It is possible to tune the Linux network stack by increasing the network buffers ...

    • Building goal-specific quantum circuits with evolutionary algorithms 

      Bhandari, Shailendra (Master thesis, 2023)
      This thesis investigates the potential of bio-inspired evolutionary algorithms for designing quantum circuits that prepare highly entangled quantum states. Entanglement is a crucial quantum property and a valuable resource ...

    • CA-NEAT: Evolved Compositional Pattern Producing Networks for Cellular Automata Morphogenesis and Replication 

      Nichele, Stefano; Ose, Mathias Berild; Risi, Sebastian; Tufte, Gunnar (Journal article; Peer reviewed, 2017)
      Cellular Automata (CA) are a remarkable example of morphogenetic system, where cells grow and self-organise through local interactions. CA have been used as abstractions of biological development and artificial life. Such ...

    • Canonical Computations in Cellular Automata and Their Application for Reservoir Computing 

      Lindell, Trym; Hudcová, Barbora; Nichele, Stefano (Peer reviewed; Journal article, 2023)
      Cellular Automata (CAs) have potential as powerful parallel computational systems, which has lead to the use of CAs as reservoirs in reservoir computing. However, why certain Cellular Automaton (CA) rules, sizes and input ...

    • Comparison and benchmarking of reservoir computing using cellular automata and random boolean networks as substrates 

      Jahren, Ruben (ACIT;2022, Master thesis, 2022)
      Reservoir Computing is an emerging concept in artificial intelligence derived from Recurrent Neural Networks, which utilizes an untrained reservoir substrate to memorize and separate input in such a way that it may be ...

    • Criticality as a measure of developing proteinopathy in engineered human neural networks 

      Valderhaug, Vibeke Devold; Heiney, Kristine; Huse Ramstad, Ola; Bråthen, Geir; Kuan, Wei-Li; Nichele, Stefano; Sandvig, Axel; Sandvig, Ioanna (bioRxiv;, Journal article, 2020-05-04)
      A patterned spread of proteinopathy represents a common characteristic of many neurodegenerative diseases. In Parkinson’s disease (PD), misfolded forms of alpha-synuclein proteins aggregate and accumulate in hallmark ...

    • Criticality-Driven Evolution of Adaptable Morphologies of Voxel-Based Soft-Robots 

      Talamini, Jacopo; Medvet, Eric; Nichele, Stefano (Frontiers in Robotics and AI;1 June 2021 | Volume 8 | Article 673156, Peer reviewed; Journal article, 2021-06-17)
      The paradigm of voxel-based soft robots has allowed to shift the complexity from the control algorithm to the robot morphology itself. The bodies of voxel-based soft robots are extremely versatile and more adaptable than ...

    • Deep learning with cellular automaton-based reservoir computing 

      Nichele, Stefano; Molund, Andreas (Complex Systems;Volume 26, Issue 4, Journal article; Peer reviewed, 2017)
      Recurrent neural networks (RNNs) have been a prominent concept wiithin artificial intelligence. They are inspired by biological neural net works (BNNs) and provide an intuitive and abstract representation of how BNNs work. ...

    • A deep learning-based tool for automatic brain extraction from functional magnetic resonance images of rodents 

      Gulden Dahl, Annelene; Nichele, Stefano; Mello, Gustavo (Peer reviewed; Journal article, 2021)
      Removing skull artifacts from functional magnetic images (fMRI) is a well understood and frequently encountered problem. Because the fMRI field has grown mostly due to human studies, many new tools were developed to handle ...

    • The Dynamical Landscape of Reservoir Computing with Elementary Cellular Automata 

      Glover, Tom Eivind; Lind, Pedro; Yazidi, Anis; Osipov, Evgeny; Nichele, Stefano (Conference object, 2021)
      Reservoir Computing with Cellular Automata (ReCA) is a promising concept by virtue of its potential for efficient hardware implementation and theoretical understanding of Cellular Auotmata (CA). However, ReCA has so far ...

    • Early functional changes associated with alpha-synuclein proteinopathy in engineered human neural networks 

      Valderhaug, Vibeke Devold; Heiney, Kristine; Huse Ramstad, Ola; Bråthen, Geir; Kuan, Wei-Li; Nichele, Stefano; Sandvig, Axel; Sandvig, Ioanna (American Journal of Physiology - Cell Physiology;, Peer reviewed; Journal article, 2021-06-18)
      A patterned spread of proteinopathy represents a common characteristic of many neurodegenerative diseases. In Parkinson’s disease (PD), misfolded forms of alpha-synuclein proteins accumulate in hallmark pathological ...

    • Emotion recognition using multi-modal data and machine learning techniques: A tutorial and review 

      Zhang, Jianhua; Yin, Zhong; Chen, Peng; Nichele, Stefano (Information Fusion;Volume 59, July 2020, Peer reviewed; Journal article, 2020-01-31)
      In recent years, the rapid advances in machine learning (ML) and information fusion has made it possible to endow machines/computers with the ability of emotion understanding, recognition, and analysis. Emotion recognition ...

    • Ethics of artificial intelligence demarcations 

      Hansen, Anders Braarud; Nichele, Stefano (Communications in Computer and Information Science;1056, Chapter; Peer reviewed, 2019)
      In this paper, we present a set of key demarcations, particularly important when discussing ethical and societal issues of current AI research and applications. Properly distinguishing issues and concerns related to ...

    • Evading a Machine Learning-based Intrusion Detection System through Adversarial Perturbations 

      Fladby, Torgeir; Haugerud, Hårek; Nichele, Stefano; Begnum, Kyrre; Yazidi, Anis (RACS: Research in Applied Computation Symposium; RACS '20: International Conference on Research in Adaptive and Convergent Systems, Chapter; Peer reviewed; Conference proceeding, 2020-10)
      Machine-learning based Intrusion Detection and Prevention Systems provide significant value to organizations because they can efficiently detect previously unseen variations of known threats, new threats related to known ...

    • EvoDynamic: A Framework for the Evolution of Generally Represented Dynamical Systems and Its Application to Criticality 

      Pontes-Filho, Sidney; Lind, Pedro; Yazidi, Anis; Zhang, Jianhua; Hammer, Hugo Lewi; Mello, Gustavo; Sandvig, Ioanna; Tufte, Gunnar; Nichele, Stefano (Lecture Notes in Computer Science;Volume 12104, Conference object, 2020-04-09)
      Dynamical systems possess a computational capacity that may be exploited in a reservoir computing paradigm. This paper presents a general representation of dynamical systems which is based on matrix multiplication. That ...

    • Evolved Art with Transparent, Overlapping, and Geometric Shapes 

      Berg, Joachim; Berggren, Nils Gustav Andreas; Borgeteien, Sivert; Jahren, Christian; Sajid, Arqam; Nichele, Stefano (Communications in Computer and Information Science;Volume 1056, Conference object, 2019-11-22)
      In this work, an evolutionary art project is presented where images are approximated by transparent, overlapping and geometric shapes of different types, e.g., polygons, circles, lines. Genotypes representing features and ...