Sökning: "Hebbian learning"

Visar resultat 6 - 10 av 11 avhandlingar innehållade orden Hebbian learning.

  1. 6. 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. 7. Biologically-Based Interactive Neural Network Models for Visual Attention and Object Recognition

    Författare :Mohammad Saifullah; Arne Jönsson; Christian Balkenius; Anders Lansner; Linköpings universitet; []
    Nyckelord :Biologically-Based Models; Object Recognition; Visual Attention; Interactive Neural Network; Occlusion; Overlapping;

    Sammanfattning : The main focus of this thesis is to develop biologically-based computational models for object recognition. A series of models for attention and object recognition were developed in the order of increasing functionality and complexity. LÄS MER

  4. 8. Modeling prediction and pattern recognition in the early visual and olfactory systems

    Författare :Bernhard Kaplan; Lansner Anders; Fred Hamker; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; spiking neural networks; pattern recognition; self-organization; prediction; anticipation; visual system; olfactory system; modeling; Computer Science; Datalogi;

    Sammanfattning : Our senses are our mind's window to the outside world and determine how we perceive our environment.Sensory systems are complex multi-level systems that have to solve a multitude of tasks that allow us to understand our surroundings. LÄS MER

  5. 9. Non-linear synaptic integration on dendrites of striatal medium-spiny neuron : a computational study

    Författare :Kai Du; Karolinska Institutet; Karolinska Institutet; []
    Nyckelord :;

    Sammanfattning : Striatum is the main input nucleus of basal ganglia. Medium-spiny neurons (MSNs), the principal neurons of the striatum, receive convergent excitatory inputs from cortex and thalamus, thus “gate” the information flow to the basal ganglia. LÄS MER

  7. 10. Extra- and intracellular electronic conductance of signals and its significance for synaptic plasticity

    Författare :Isaac Shemer; Karolinska Institutet; Karolinska Institutet; []
    Nyckelord :;

    Sammanfattning : Electrical signals play a pivotal role in the normal function of most if not all organisms. Understanding the electrophysiological principles that govern electrical signaling is essential for insights into normal- and pathological processes in cell biology. LÄS MER