Scribd Logo
Upload

Welcome to Scribd!

  • 10 views

    Class 8

    Uploaded by

    sm737744

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Class 8

    Uploaded by

    sm737744
    10 views8 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    10 views8 pages

    Class 8

    Uploaded by

    sm737744

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    You are on page 1of 8

    Neural circuits

    • CNS contains billions of neurons organized into complicated networks called neural circuits.
    • These are functional groups of neurons that process specific types of information.

    • The simplest neural circuit may consist of one series connection, but in most cases they are very complex.

    These are not branches of trees, but neural circuits of our brain …
    Neural circuits: types
    Definitions
    Diverging – A single presynaptic neuron may synapse with several postsynaptic neurons.
    Example: Sensory signals are arranged in diverging circuits, allowing a sensory impulse to be
    relayed to several regions of the brain. This arrangement amplifies the signal.

    Converging – Several presynaptic neurons synapse with a single post synaptic neuron. This
    arrangement permits more effective simulation or inhibition of the postsynaptic neuron.
    Example: A single motor neuron that synapses with skeletal muscle fibres at neuromuscular
    junctions receives input from several pathways that originate in different brain regions.

    Reverberating – Branches from later neurons synapse with earlier ones, thereby sending impulses
    back through the circuit again and again.
    Example: The activities of breathing and waking up are considered to be a result of such circuit.

    Parallel after-discharge – A single presynaptic cell stimulates a group of neurons, each of which
    synapses with a common postsynaptic cell.
    Example: Mathematical calculations.
    Plasticity and Regeneration

     The nervous system exhibits capabilities to change based on experience. This property of
    the neurons is called plasticity. This changes may include sprouting of new dendrites,
    synthesis of new proteins, and changes in synaptic contacts with other neurons. Both
    chemical and electrical signals drive these changes.

     The regeneration of neurons is the capability to replicate or repair themselves. Mammalian


    neurons have limited capacity to regenerate. In PNS, damage to dendrites and axons may be
    repaired to certain extent if the cell body and the Schwann cells remain active. However,
    CNS exhibits little or no repair to the damage.
    Artificial Neural Network (ANN)
    An artificial neuron network (ANN) is a computational model based on the structure
    and functions of biological neural networks. Information that flows through the
    network affects the structure of the ANN because a neural network changes - or
    learns, in a sense - based on that input and output.

     ANNs are considered nonlinear statistical data modelling tools where the
    complex relationships between inputs and outputs are modelled or patterns
    are found.

     ANN can actually learn from observing data sets. In this way, it is used as a
    random function approximation tool.

     Training an artificial neural network involves choosing from allowed models


    for which there are several associated algorithms.

     Usage: Machine Learning, Artificial Intelligence


    Structure of ANN

    Backpropagation, short for "backward propagation of errors," is an algorithm for


    supervised learning of artificial neural networks using gradient descent. Given an
    artificial neural network and an error function, the method calculates the gradient
    of the error function with respect to the neural network's weights.
    Back-propagation Neural Network (BPNN)

    a1: constant of activation function


    for input neurons

    a2: constant of activation function


    for hidden neurons

    a3: constant of activation function


    for output neurons

    b: bias value

    You might also like