MATLAB: How to multiply the input vector and weight matrix (X*iw+b)

anninputiw

Mr greg suggested output = repmat(b2,1,N) + LW*tanh(repmat(b1,1,N)+ IW*input). in this equation i am having 3 input and iw matrix of size 20X3.how to multiply three inputs vector and weight matrix

Best Answer

The MAT in MATLAB stands for MATRIX. If

 size(IW) = [ 20 3 ]
 size(x)  = [ 3  N ]

Then the matrix multiplication command yields

size(IW*x) = [ 20 N ];

Hope this helps.

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: How to put a Matrix in the inputs of the neural network

Typically N I-dimensional "I"nput vectors are paired with N O-dimensional "O"utput target vectors and stored in matrices with sizes

 [ I N ]   = size(input)
 [ O N ]   = size(target)
 net = fitnet;

% Equivalent to net = fitnet(H) for H = 10 where H is the number of hidden nodes

 [ net tr output error ] = train(net,input,target);

% where tr is the training record, output = net(input) and error = target-output;

See the documentation

 help fitnet
 doc fitnet

Hope this helps.

Thank you for formally accepting my answer

Greg

MATLAB: How are the input weights organized in a nonlinear autoregressive networks with an external input (narxnet)

    close all, clear all, clc;
    net = narxnet(10:15,10:15,10)      % Removed semicolon
    % net.numInputs = 2                % Input and Output Feedback
    % net.numInputDelays = 15          % BUG? Not 2*length(10:15) = 12?
    % net.numFeedbackDelays = 0        % Open Loop
    % net.numWeightElements = 10 % 10 zero bias weights (I & O not configured)
    IWc = net.IW                 % 2 inputs
    LWc = net.LW
    bc = net.b
    IW = cell2mat(IWc)           % BUG? No indication of 2 inputs
    LW = cell2mat(LWc)
    b = cell2mat(bc)
    view(net)
    [X,T] = simplenarx_dataset;
    [Xs,Xi,Ai,Ts] = preparets(net,X,{},T);
    rng(0)                                 % So you can duplicate results
    [net tr Ys Es ]=  train(net,Xs,Ts,Xi,Ai);   % ALWAYS include tr !!!
    IWc = net.IW
    LWc = net.LW
    bc = net.b
    IW = cell2mat(IWc)               % [10 12] = size( IW)
    LW = cell2mat(LWc)               % [ 1 10] = size( LW)
    b = cell2mat(bc)                 % [11  1] = size( b)
    view(net)
    tr = tr                          % For your edification
    %      Hope this helps
    %

    %      Thank you for formally accepting my answer
    %
    %      Greg

Related Question