Sökning: "Autoassociative Memory"

Hittade 4 avhandlingar innehållade orden Autoassociative Memory.

  1. 1. An Attractor Memory Model of Neocortex

    Författare :Christopher Johansson; Anders Lansner; Stefano Fusi; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Attractor Neural Networks; Cerebral Cortex; Neocortex; Brain Like Computing; Hypercolumns; Minicolumns; BCPNN; Parallel Computers; Autoassociative Memory; Computer science; Datalogi;

    Sammanfattning : This thesis presents an abstract model of the mammalian neocortex. The model was constructed by taking a top-down view on the cortex, where it is assumed that cortex to a first approximation works as a system with attractor dynamics. LÄS MER

  3. 2. Some computational aspects of attractor memory

    Författare :Martin Rehn; Anders Lansner; Magnus Borga; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Datalogi; attractor memory; cerebral cortex; neural networks; Datalogi; Computer science; Datalogi;

    Sammanfattning : In this thesis I present novel mechanisms for certain computational capabilities of the cerebral cortex, building on the established notion of attractor memory. A sparse binary coding network for generating efficient representation of sensory input is presented. LÄS MER

  4. 3. Aspects of memory and representation in cortical computation

    Författare :Martin Rehn; Anders Lansner; Örjan Ekeberg; Peter Földiák; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; cerebral cortex; neural networks; attractor memory; sequence learning; biological vision; generative models; serial order; computational neuroscience; dynamical synapses; Computer science; Datalogi;

    Sammanfattning : Denna avhandling i datalogi föreslår modeller för hur vissa beräkningsmässiga uppgifter kan utföras av hjärnbarken. Utgångspunkten är dels kända fakta om hur en area i hjärnbarken är uppbyggd och fungerar, dels etablerade modellklasser inom beräkningsneurobiologi, såsom attraktorminnen och system för gles kodning. LÄS MER

  5. 4. Towards Cortex Isomorphic Attractor Neural Networks

    Författare :Christopher Johansson; KTH; []
    Nyckelord :Attractor Neural Networks; Cerebral Cortex; Minicolumns; Hypercolumns; Potts Neural Networks; BCPNN; and Parallel Computers;

    Sammanfattning : In this thesis we model the mammalian cerebral cortex withattractor neural networks and study the parallelimplementations of these models. First, we review the size, structure, and scaling laws ofthe cerebral cortex of five mammals; mouse, rat, cat, macaque,and human. LÄS MER