Sökning: "Biologically-Inspired models"

Hittade 4 avhandlingar innehållade orden Biologically-Inspired models.

  1. 1. Exploring Biologically-Inspired Interactive Networks for Object Recognition

    Författare :Mohammad Saifullah; Arne Jönsson; Rita Kovordányi; Christian Balkenius; Linköpings universitet; []
    Nyckelord :Interactive neural networks; Biologically-Inspired models; Visual attention; Object recognition.; TECHNOLOGY; TEKNIKVETENSKAP;

    Sammanfattning : This thesis deals with biologically-inspired interactive neural networks for the task of object recognition. Such networks offer an interesting alternative approach to traditional image processing techniques. Although the networks are very powerful classification tools, they are difficult to handle due to their bidirectional interactivity. LÄS MER

  3. 2. Learning from Interactions : Forward and Inverse Decision-Making for Autonomous Dynamical Systems

    Författare :Inês de Miranda de Matos Lourenço; Bo Wahlberg; Sandra Hirche; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Intelligent systems; autonomous decision-making; Reinforcement Learning; Markov models; Human-Robot Interaction; Biologically-inspired systems; Electrical Engineering; Elektro- och systemteknik;

    Sammanfattning : Decision-making is the mechanism of using available information to generate solutions to given problems by forming preferences, beliefs, and selecting courses of action amongst several alternatives. In this thesis, we study the mechanisms that generate behavior (the forward problem) and how their characteristics can explain observed behavior (the inverse problem). LÄS MER

  4. 3. Accessibility percolation and first-passage percolation on the hypercube

    Författare :Anders Martinsson; Göteborgs universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; hypercube; percolation; accessible path; house of cards; rough mount Fuji; first-passage percolation; Richardson s model; branching translation process; hypercube;

    Sammanfattning : In this thesis, we consider two percolation models on the n-dimensional binary hypercube, known as accessibility percolation and first-passage percolation. First-passage percolation randomly assigns non-negative weights, called passage times, to the edges of a graph and considers the minimal total weight of a path between given end-points. LÄS MER

  5. 4. On large-scale neural simulations and applications in neuroinformatics

    Författare :Simon Benjaminsson; Anders Lansner; Marc-Oliver Gewaltig; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

    Sammanfattning : This thesis consists of three parts related to the in silico study of the brain: technologies for large-scale neural simulations, neural algorithms and models and applications in large-scale data analysis in neuroinformatics. All parts rely on the use of supercomputers. LÄS MER