Comparison Between Neural Network and Computer

Embed Size (px)

Citation preview

  • 7/29/2019 Comparison Between Neural Network and Computer

    1/14

    PRESENTED BY

    PANKAJ SHARMA

    SEMINAR

    COMPARISON BETWEEN NEURAL

    NETWORKS AND COMPUTER

  • 7/29/2019 Comparison Between Neural Network and Computer

    2/14

    What is a Neural Network?

    Neural network is collection of highlyinterconnected processing elements calledneurons.

    Neural networks are inspired by the waybiological nervous system such as brainprocess information.

    Neural networks learn by example.

  • 7/29/2019 Comparison Between Neural Network and Computer

    3/14

    Basic structure of Brain

  • 7/29/2019 Comparison Between Neural Network and Computer

    4/14

    Specifications of brain

    Number of Neurons 100 billion

    Number of

    synapses/neuron

    1000

    Total number of synapses 100000 billion

    Operations/s/neuron 100

    Total operations 10000 trillion

    Brain weight 1.5 kg

  • 7/29/2019 Comparison Between Neural Network and Computer

    5/14

    Characteristics of ANN

    Parallel computation: program is executedsimultaneously.

    Robustness: insensitive to partial inputs.

    Self learning: algorithm is created itself.

    Fault tolerance: output is not affected ifone or two neuron are damaged.

  • 7/29/2019 Comparison Between Neural Network and Computer

    6/14

    Basic model of an ANNx1*w1 + x2*w2 + > th

  • 7/29/2019 Comparison Between Neural Network and Computer

    7/14

    Learning in ANN

  • 7/29/2019 Comparison Between Neural Network and Computer

    8/14

    Precautions before learning process

    1. Decide the function of neural network to beperformed.

    2. Make a complete set of input and outputpatterns.

    3. Determine the number of layers in networkand number of nodes per layer.

    4. Select the appropriate threshold value.5. Determine the algorithm termination

    criteria.

  • 7/29/2019 Comparison Between Neural Network and Computer

    9/14

    Applications of neural networks

    1. In signal processing.

    2. Image data processing.

    3. Communication systems.

    4. Intelligent control.5. Optimization techniques.

  • 7/29/2019 Comparison Between Neural Network and Computer

    10/14

    Computer: essential characteristics

    The problem to be solved should have somemathematical solution.

    All the steps for solving any problem shouldbe explicitly specified.

    The data should have a precise format.

    There should not be any memory crash.

  • 7/29/2019 Comparison Between Neural Network and Computer

    11/14

    Steps in computing

    1. Fetch an instruction from memory.

    2. Fetch any data required by the instructionfrom memory.

    3. Execute the instruction.

    4. Store the result in memory.

    5. go to step 1

  • 7/29/2019 Comparison Between Neural Network and Computer

    12/14

    Computer: advantage and limitation

    1. Advantage:

    Fast arithmetic.

    Do precisely what the programmer wants to do.

    Makes life easier.

    2. Limitation :

    Not fault tolerance.

    Cannot solve a problem without a mathematicalsolution.

    No parallelism.

    Cannot adapt according to circumstances.

  • 7/29/2019 Comparison Between Neural Network and Computer

    13/14

    Comparison between computer and

    neural network1. Problem solving approach : in most of cases computer uses top -

    down approach in problem solving. Whereas neural network usesbottom up approach in problem solving.

    2. Way of functioning : computers function logically with a set of rulesand calculations whereas neural networks can function via images ,pictures and concepts.

    3. Self programming : computers need some algorithm for problem

    solving , whereas neural network learns by itself.

    4. Speed : speed of computer depends on various aspects of processor, whereas neural network use chips for different applications.

  • 7/29/2019 Comparison Between Neural Network and Computer

    14/14

    if (IsTired()) {GoToSleep();}

    else {StayAwake();}

    A revised version:if (IsTired()) {

    if (!IsInClass() && !WorkingOnProject()) {

    GoToSleep(); }

    else { if (IsInClass()) {Stay Awake(); }

    else { if (WorkingOnProject()) {

    if (AssignmentIsDueTomorrow()) {

    if (AssignmentIsCompleted()) {

    GoToSleep(); }

    else { StayAwake(); } }

    else { GoToSleep(); } }

    else { StayAwake(); } }}

    else {StayAwake();}