How to create a table in Matlab? - matlab

Following is the graph that I used to calculate the PMV at points: A, B, C, D, E
%This is the code I used to calculate the PMV at points: A, B, C, D, E.
%Where:
%ta=tr=interior temperature setting (22°C, 23°C, 27°C) (variable);
%va=0,2 m/s (invariable);
%RH=50% (invariable);
%W=0 (invariable);
%Met= energy metabolism (1,2 met or 1,4 met) (variable);
%Iclo= static clothing insulation (0,5 clo or 1,0 clo) (variable).
ta=22.0;
tr=22.0;
va=0.2; %air speed
RH=50; %relative humidity
W=0;%mechanical work
Met=1.2;%energy metabolism in met (1 met=58.2 W/m2)
Iclo=0.5;%static clothing insulation
%preparation of variables
PHI=RH/100;%hygrometric dimensionless degree
Icl=Iclo*.155;%Conversion from clo to m2K/W
M=Met*58.15;%conversion of metabolism in unit of measurement of SI
Iclr=Icldyn_7730(va, Icl, M); %calculation of dynamic clothing insulation
vw=0.0052*(M-58);
vr=va+vw;
PMV_Fanger=PMV_evaluator( M,W,ta,tr,vr,PHI,Iclr );
Observation: the functions I called are the following: "Icldyn_7730"
function [ Icldyn ] = Icldyn_7730(va, Iclst, M)
%calculation of dynamic clothing insulation
%Input data
% va, air speed, m/s
% Iclst, static clothing insulation
% M, metabolism in W/m2
vw=0.0052*(M-58);
if vw>0.7
vw=0.7;
end
vr=va+vw;
%Static cloting insulation conversion m2K/W to clo
Iclo = Iclst/0.155;
%Clothing area factor
if Iclst <=0.078
fcl= 1.00 + 1.290 * Iclst;
else
fcl= 1.05 + 0.645 * Iclst;
end
%Static boundary layer thermal insulation in quiet air in m2K/W
Iast = 0.111;
%Total static insulation
Itotst= Iclst + Iast / fcl;
%Clothing insulation correction for wind (vr) and and walking (vw)
vraux= vr;
if vraux > 3.5
vraux=3.5;
end
if vraux < 0.15
vraux=0.15;
end
vwaux=vw;
if vwaux>0.7
vwaux=0.7;
end
CorIt=exp(-0.281*(vraux-0.15)+0.044*(vraux-0.15)^2-0.492*vwaux+0.176*vwaux^2);
if CorIt>1
CorIt=1;
end
CorIa=exp(-0.533*(vraux-0.15)+0.069*(vraux-0.15)^2-0.462*vwaux+0.201*vwaux^2);
if CorIa>1
CorIa=1;
end
Itr = Itotst * CorIt;
Iar = CorIa * Iast;
if Iclo<=0.6
Itr= ((0.6-Iclo) * Iar + Iclo * Itr) / 0.6;
end
Itdyn = Itr;
Iadyn = Iar;
Icldyn = Itdyn - Iadyn / fcl;
end
and "PMV_evaluator"
function [ PMV ] = PMV_evaluator( M,W,ta,tr,vr,PHI,Icl )
%Function for the calculation of the PMV index
% Input data
% M, metabolic rate in W/m2
% W, mechanical work in W/m2
% ta, air temperature in °C
% tr, mean radiant temperature in °C
% vr, rwlative air velocity in m/s
% PHI, hygrometric ratio dimensionless
% Icl in m2K/W (dynamic clothing insulation )
if (ta >=0)
ps = exp (16.6536-4030.183 / (235 + ta ));
else
ps = 0.6105* exp (21.875*ta / (265.5 + ta ));
end;
TAA = ta+273.0;
TRA = tr+273.0;
TCLA = TAA + (35.5-ta) / (3.5*Icl+0.1);
hcf = 12.1 * sqrt(vr);
%Clothing area factor
if Icl <=0.078
fcl= 1.00 + 1.290 * Icl;
else
fcl= 1.05 + 0.645 * Icl;
end
% Start of the loop for the evaluation of clothing surface temperature}
P1 = Icl * fcl;
P2 = P1 * 3.96;
P3 = P1 * 100;
P4 = P1 * TAA;
P5 = 308.7 - 0.028 * (M-W) + P2 * (TRA/100)^4;
XN = TCLA/100;
XF = XN;
EPS = 0.00015;
CONV = 100;
N=1;
while (CONV>EPS)
XF = (XF+XN)/2;
hcn = 2.38 * ((abs(100*XF - TAA))).^0.25;
if (hcf<=hcn)
hc = hcn;
else
hc = hcf;
end
XN = (P5+P4*hc-P2*XF^4)/(100+P3*hc);
CONV=abs(XF-XN);
end
tcl = 100*XN-273;
% End of the loop for the evaluation of clothing surface temperature}
%Skin diffusion heat loss
HL1=3.05*0.001*(5733-6.99*(M-W)-1000*PHI*ps);
%Sweat heat loss
if (M-W)>58.15
HL2= 0.42 * ((M-W)-58.15);
else
HL2=0;
end
%Respiration latent heat loss
HL3= 1.7*0.00001 * M * (5867-1000*PHI*ps);
%Respiration dry heat loss
HL4= 0.0014 * M * (34-ta);
%Radiative heat loss
HL5= 3.96 * fcl * ((0.01*tcl+2.73)^4-(0.01*tr+2.73)^4);
%Convective heat loss
HL6= fcl * hc * (tcl-ta);
%Thermal sensation transformation coefficient}
TS= 0.303 * exp(-0.036*M) + 0.028;
PMV= TS * (M-W-HL1-HL2-HL3-HL4-HL5-HL6);
end
How can I create a table like the following with MATLAB?
The data in the table are the values of PMV. They have been obtained from the individual calculations of MATLAB.

Consider using the table variable introduced in the later versions of matlab, this variable allows for disparate data sources. The full matlab help has an example where the a set of categorical row names occupies the first column while a set of headers occupies the top.
The writetable commmand in matlab will also write a table variable (rows/columns/headers etc) to an excel spreadsheet.

Verbosing zhqiat's answer, your table could be generated by the following code:
data = [-1.5924 -0.2152 -1.1426 0.0421; -1.5924 -0.2152 -1.1426 0.0421; -1.2319 0.0313 -0.8241 0.2595; 0.2329 1.0332 0.4686 1.1427; 0.2329 1.0332 0.4686 1.1427];
row_names = {'A', 'B', 'C', 'D', 'E'};
var_names = {'met1d2_clo0d5', 'met1d2_clo1d0', 'met1d4_clo0d5', 'met1d4_clo1d0'};
var_description = {'M = 1.2 met - 0.5 clo', 'M = 1.2 met - 1. clo', 'M = 1.4 met - 0.5 clo', 'M = 1.4 met - 1.0 clo' };
testtable = array2table(data, 'VariableNames', var_names, 'RowNames', row_names);
testtable.Properties.VariableDescriptions = var_description;
This would result in something like this:
Screenshot of Matlab-Table
We all might got your question wrong. So please try to refine it, if the right answers are missing.

Related

How to solve a System of 8 ODEs in Matlab where for 4 ODEs initial value is at height z=0 and for rest initial value is at z = H

I have a reactor in which solid is charged from top and gas is charged from the bottom.
I have provided the initial values of them (i.e I know the initial value of solid entities at the top and initial values of gases at the bottom). To solve the heat and mass balance equations I wrote 8 ODEs.
But how can I solve them simultaneously?
Some ODEs initial value is at z=0, and for some other initial value z it is at z = H; where H is the height of the furnace.
function f = odefun( Z,Y )
% FeO + CO -> Fe + CO2 ---(1)
% C + 1/2 O2 -> CO ---(2)
% C + O2 -> CO2 ---(3)
% C + CO2 -> 2CO ---(4)
Fg = Y(1); %volumetic flow rate of gas Nm3s-1 //initialize
Cfeo = Y(2); % initial FeO concentration mol/m3
Cc = Y(3); % initial C concentration mol/m3
yco = Y(4); % mole fraction of CO initially
yco2 = Y(5); % mole fraction of CO2 initially
yo2 = Y(6); % mole fraction of O2 initially
Tg = Y(7); % temp of gas K
Ts = Y(8); % temp of solid K
Fs = 0.044; %Mass flow rate of solid m3/s //initialize and constant
P = 5; %total pressure atm
R = 8.314; %gas constant
M = 104; %molecular mass //constant
keqm1 = 3.33; %equilibrium constant for rx 1
keqm2 = 3 * 10^10; %equilibrium constant for rx 2
keqm3 = 4.75 * 10^20; %equilibrium constant for rx 3
Az = 4; %area of the bed m2 //constant
e = 0.4; %voidage //constant
O = 0.6; %Avg shape factor of solid particle //constant
dp = 0.02; %diameter of particles // constant m
Cpg = 293000; %specific heat capacity of gas (JKg-1K-1) //constant
Cps = 440000; %specific heat capacity of solid (JKg-1K-1) //assume constant
mu = 0.005; %viscosity of gas Kg m-1 s-1 //assume constant
a = 10; %surfce area of DRI per unit volume of bed
Ac = 20; % surfce area of coal per unit volume
hgs = 200; %heat transfer coefficient b/w solid and gas J m-2 s-1 K-1
H1 = -16000; %enthalpy of reaction 1 KJ mol-1
H2 = -110520; %enthalpy of reaction 2 KJ mol-1
H3 = -393509; %enthalpy of reaction 3 KJ mol-1
H4 = -282989; %enthalpy of reaction 4 KJ mol-1
C0 = 28/22.4; % Kg/m3
C1 = 44/22.4;
C2 = 32/22.4;
Dg = (C0 * yco + C1 * yco2 + C2 * yo2); %Density of Gas Kg m-3
Db = (1-e)*(Cfeo*72 + (Y(2) - Cfeo)*56 + Cc*12 )*1000 ; %Density of Bed Kg m-3
Re = (Dg * Fg * e * dp)/(mu*Az) ; %Reynolds number
f1 = (150 * (1-e)^2 * mu)/(e^2 * Dg * dp^2); %friction factor parameter
f2 = (1.75*(1-e))/(e^3 * Dg * dp);
dFgdZ = -(Fg/(P * Az^2))*(f1*Az*Fg + f2 * Fg^2); %volumetric flow rate of gas Nm3 s-1
kp1 = 2.5*exp(-8857.6/Ts); % chemical rxn rate constant s-1
kp2 = 6.52*10^(5) * exp(-22000/Ts) * Ts^(0.5);
kp3 = kp2;
kp4 = 4*10^12 * exp(-40000/Ts);
Vg = yco + yco2; %mass fraction of volatile evolve
kf = 2.0*Re^(-0.336)* Vg; %mass transfer coefficient m/s
Po2 = yo2; % partial pressure atm
Pco = yco;
Pco2 = yco2;
Pco2eqm = 0.2; % Change
Pre2 = (Po2 - (Pco^(2)/keqm2^(2))); % driving force atm
Pre3 = (Po2 - (Pco2^(2)/keqm3^(2)));
Pre4 = (Pco2 - Pco2eqm);
R1 = a*(Fs/Y(1))^(1/3)*kp1*(yco-yco2/keqm1)*P/(R*Ts); %reaction rate constant m-3s-1
R2 = (Ac/((6/(dp*kp2))+(1/kf))) * (9.869*10^(-6)*Pre2)/(M*R*Ts);
R3 = (Ac/((6/(dp*kp3))+(1/kf))) * (9.869*10^(-6)*Pre3)/(M*R*Ts);
R4 = (Ac/((6/(dp*kp4))+(1/kf))) * (9.869*10^(-6)*Pre4)/(M*R*Ts);
dCfeodZ = (R1*Az*(1-e))/Fs; %for FeO Cfeo Kg/s
dCcdZ = ((R2+R3+R4)*Az*(1-e))/Fs; %for C
dycodZ = 22.4*Az*(R2*(yco/2 - 1)+(yco - 2)+R1)/Fg; %for CO
dyco2dZ = 22.4*Az*(yco2*(R2/2 + R4)+R4-R1-R3)/Fg; %for CO2
dyo2dZ = 22.4*Az*(R2/2 + R3 + yo2*(R2/2 + R4))/Fg; %for O2
%Heat transfer equations
S = (6*(1-e)*Az)/(dp*O) ; %surface area of the solid
B = (6*(1-e)*hgs)/(dp*O);
A = 16*R1+12*(R2+R3+R4);
E = H1*R1+ H2*R2+ H3*R3+ H4*R4;
dTgdZ = (22.4/(Fg*Cpg))*(Az*Cpg*Tg*(R2/2 + R4)+ S*(Tg - Ts)*hgs );
dTsdZ = (Az*(1-e)/(Fs*Cps*Db))*(A*Cps*Ts + B*(Tg - Ts) - E);
f = [dFgdZ;dCfeodZ;dCcdZ;dycodZ;dyco2dZ;dyo2dZ;dTgdZ;dTsdZ];
end
These is the function with ODES and the initial values of Fg(z=0), Cfeo(z=H),Cc(z=H) yco(z=0),yco2(z=0),yo2(z=0),Tg(z=0),Ts(z=H) are provided kindly help me out to solve this problem.

Matlab ode45 new variable

I have a Matlab code that simulates frisbee flight dynamics. I would like to add a wind variable. I did it, but after seeing the plots I think my wind is reducing the speed of the disc. I mean it should change the speed of the disc but via lift and drag force, now it looks like wind speed variable direcly changes disc speed variable. What I want is to affect only the lift and drag forces with wind, but I can't make it work. Here is my current code that is not working. This is an external M-file which is used by the ode45 function in the main script:
[t,x]=ode45(#discfltEOM,tspan,x0,options,CoefUsed);
function xdot=discfltEOM(t,x,CoefUsed)
% Equations of Motion for the frisbee
% The inertial frame, xyz = forward, right and down
global m g Ia Id A d rho
global CLo CLa CDo CDa CMo CMa CRr
global CL_data CD_data CM_data CRr_rad CRr_AdvR CRr_data
global CMq CRp CNr
% x = [ x y z vx vy vz f th fd thd gd gamma Wx Wy]
% 1 2 3 4 5 6 7 8 9 10 11 12 13 14
%% give states normal names
vx = x(4);
vy = x(5);
vz = x(6);
f = x(7);
th = x(8);
st = sin(th);
ct = cos(th);
sf = sin(f);
cf = cos(f);
fd = x(9);
thd= x(10);
gd = x(11);
Wx = x(13);
Wy = x(14);
%% Define transformation matrix
%% [c]=[T_c_N] * [N]
T_c_N=[ct st*sf -st*cf; 0 cf sf; st -ct*sf ct*cf];
%% [d]=[T_d_N] * [N]
%T_d_N(1,:)=[cg*ct sg*cf+sf*st*cg sf*sg-st*cf*cg];
%T_d_N(2,:)=[ -sg*ct cf*cg-sf*sg*st sf*cg+sg*st*cf];
%T_d_N(3,:)=[ st -sf*ct cf*ct]
[evec,eval]=eig(T_c_N);
eigM1=diag(eval);
m1=norm(eigM1(1));
m2=norm(eigM1(2));
m3=norm(eigM1(3));
c1=T_c_N(1,:); % c1 expressed in N frame
c2=T_c_N(2,:); % c2 expressed in N frame
c3=T_c_N(3,:); % c3 expressed in N frame
%% calculate aerodynamic forces and moments
%% every vector is expressed in the N frame
vel = [vx vy vz]; %expressed in N
vmag = norm(vel);
Vwiatr = [Wx Wy 0];
Vw = norm(Vwiatr);
vc3=dot(vel,c3); % velocity (scalar) in the c3 direction
vp= [vel-vc3*c3]; % subtract the c3 velocity component to get the velocity vector
% projected onto the plane of the disc, expressed in N
alpha = atan(vc3/norm(vp));
Adp = A*rho*(vmag-Vw)*(vmag-Vw)/2;
uvel = vel/vmag; % unit vector in vel direction, expressed in N
uvp = vp/norm(vp); % unit vector in the projected velocity direction, expressed in N
ulat = cross(c3,uvp); % unit vec perp to v and d3 that points to right, right?
%% first calc moments in uvp (roll), ulat(pitch) directions, then express in n1,n2,n3
omegaD_N_inC = [fd*ct thd fd*st+gd]; % expressed in c1,c2,c3
omegaD_N_inN = T_c_N'*omegaD_N_inC'; % expressed in n1,n2,n3
omegavp = dot(omegaD_N_inN,uvp);
omegalat = dot(omegaD_N_inN,ulat);
omegaspin = dot(omegaD_N_inN,c3); % omegaspin = p1=fd*st+gd
AdvR= d*omegaspin/2/vmag ; % advanced ration
if CoefUsed==1 % using short flights coefficients
CL = CLo + CLa*alpha;
alphaeq = -CLo/CLa; % this is angle of attack at zero lift
CD = CDo + CDa*(alpha-alphaeq)*(alpha-alphaeq);
CM=CMo + CMa*alpha;
%CRr= CRr*d*omegaspinv/2./vmagv';
%CRr= CRr*sqrt(d/g)*omegaspinv; % this line produces NaN, so leave it in Mvp equation
%Mvp = Adp*d* (CRr*d*omegaspin/2/vmag + CRp*omegavp)*uvp; % expressed in N
Mvp = Adp*d*(sqrt(d/g)*CRr*omegaspin + CRp*omegavp)*uvp; % expressed in N
end % if CoefUsed==1 % using short flights coefficients
if CoefUsed==2 % using potts coefficients
%% interpolation of Potts and Crowther (2002) data
CL = interp1(CL_data(:,1), CL_data(:,2), alpha,'spline');
CD = interp1(CD_data(:,1), CD_data(:,2), alpha,'spline');
CM = interp1(CM_data(:,1), CM_data(:,2), alpha,'spline');
CRr = interp2(CRr_rad,CRr_AdvR,CRr_data,alpha,AdvR,'spline');
Mvp = Adp*d* (CRr* + CRp*omegavp)*uvp; % Roll moment, expressed in N
end % if CoefUsed==2 % using potts coefficients
lift = CL*Adp;
drag = CD*Adp;
ulift = -cross(uvel,ulat); % ulift always has - d3 component
udrag = -uvel;
Faero = lift*ulift + drag*udrag; % aero force in N
FgN = [ 0 0 m*g]'; % gravity force in N
F = Faero' + FgN;
Mlat = Adp*d*(CM + CMq*omegalat)*ulat; % Pitch moment expressed in N
Mspin = [0 0 +CNr*(omegaspin)]; % Spin Down moment expressed in C
M = T_c_N*Mvp' + T_c_N*Mlat' + Mspin'; % Total moment expressed in C
% set moments equal to zero if wanted...
% M=[0 0 0];
% calculate the derivatives of the states
xdot = vel';
xdot(4) = (F(1)/m); %accx
xdot(5) = (F(2)/m); %accy
xdot(6) = (F(3)/m); %accz
xdot(7) = fd;
xdot(8) = thd;
xdot(9) = (M(1) + Id*thd*fd*st - Ia*thd*(fd*st+gd) + Id*thd*fd*st)/Id/ct;
xdot(10) = (M(2) + Ia*fd*ct*(fd*st +gd) - Id*fd*fd*ct*st)/Id;
fdd=xdot(9);
xdot(11) = (M(3) - Ia*(fdd*st + thd*fd*ct))/Ia;
xdot(12) = x(11);
xdot(13) = Wx;
xdot(14) = Wy;
xdott=xdot';
% calculate angular momentum
H = [Id 0 0 ; 0 Id 0; 0 0 Ia]*omegaD_N_inC';
format long;
magH = norm(H);
format short;
state=x';
Wx and Wy are wind vectors. I'm trying to affect the Adp variable because it is direcly connected with lift and drag. I made Wx = 1 [m/s] and the effect is immense, but should be very little. I'm terrible with Matlab so I'm sure I making some kind of stupid mistake from not understanding well how it all works.

Matlab/CUDA: ocean wave simulation

I've studied "Simulating Ocean Water" article by Jerry Tessendorf and tried to program the Statistical Wave Model but I didn't get correct result and I don't understand why.
In my program I tried only to create a wave height field at time t = 0 without any further changes in time. After execution of my program I got not what I was expecting:
Here's my source code:
clear all; close all; clc;
rng(11); % setting seed for random numbers
meshSize = 64; % field size
windDir = [1, 0]; % ||windDir|| = 1
patchSize = 64;
A = 1e+4;
g = 9.81; % gravitational constant
windSpeed = 1e+2;
x1 = linspace(-10, 10, meshSize+1); x = x1(1:meshSize);
y1 = linspace(-10, 10, meshSize+1); y = y1(1:meshSize);
[X,Y] = meshgrid(x, y);
H0 = zeros(size(X)); % height field at time t = 0
for i = 1:meshSize
for j = 1:meshSize
kx = 2.0 * pi / patchSize * (-meshSize / 2.0 + x(i)); % = 2*pi*n / Lx
ky = 2.0 * pi / patchSize * (-meshSize / 2.0 + y(j)); % = 2*pi*m / Ly
P = phillips(kx, ky, windDir, windSpeed, A, g); % phillips spectrum
H0(i,j) = 1/sqrt(2) * (randn(1) + 1i * randn(1)) * sqrt(P);
end
end
H0 = H0 + conj(H0);
surf(X,Y,abs(ifft(H0)));
axis([-10 10 -10 10 -10 10]);
And the phillips function:
function P = phillips(kx, ky, windDir, windSpeed, A, g)
k_sq = kx^2 + ky^2;
L = windSpeed^2 / g;
k = [kx, ky] / sqrt(k_sq);
wk = k(1) * windDir(1) + k(2) * windDir(2);
P = A / k_sq^2 * exp(-1.0 / (k_sq * L^2)) * wk^2;
end
Is there any matlab ocean simulation source code which could help me to understand my mistakes? Fast google search didn't get any results.
Here's a "correct" result I got from "CUDA FFT Ocean Simulation". I didn't achieve this behavior in Matlab yet but I've ploted "surf" in matlab using data from "CUDA FFT Ocean Simulation". Here's what it looks like:
I've made an experiment and got an interesting result:
I've taken generated h0 from "CUDA FFT Ocean Simulation". So I have to do ifft to transform from frequency domain to spatial domain to plot the graph. I've done it for the same h0 using matlab ifft and using cufftExecC2C from CUDA library. Here's the result:
CUDA ifft:
Matlab ifft:
Either I don't understand some aspects of realization of cufftExecC2C or cufftExecC2C and matlab ifft are different algorithms with different results.
By the way parameters for generating such surface are:
meshSize = 32
A = 1e-7
patchSize = 80
windSpeed = 10
Well that was definitely a funny exercise. This is a completely rewritten answer since you found the issues you were asking about by yourself.
Instead of deleting my answer, there is still merit in posting to help you vectorize and/or explain a few bits of code.
I completely rewrote the GUI I gave in my former answer in order to incorporate your changes and add a couple of options. It started to grew arms and legs so I won't put the listing here but you can find the full file there:
ocean_simulator.m.
This is completely self contained and it includes all the calculating functions I vectorized and list separately below.
The GUI will allow you to play with the parameters, animate the waves, export GIF file (and a few other options like the "preset", but they are not too ironed out yet). A few examples of what you can achieve:
Basic
This is what you get with the quick default settings, and a couple of rendering options. This uses a small grid size and a fast time step, so it runs pretty quickly on any machine.
I am quite limited at home (Pentium E2200 32bit), so I could only practice with limited settings. The gui will run even with the settings maxed but it will become to slow to really enjoy.
However, with a quick run of ocean_simulator at work (I7 64 bit, 8 cores, 16GB ram, 2xSSD in Raid), it makes it much more fun! Here are a few examples:
Although done on a much better machine, I didn't use any parallel functionality nor any GPU calculations, so Matlab was only using a portion of these specs, which means it could probably run just as good on any 64bit system with decent RAM
Windy lake
This is a rather flat water surface like a lake. Even high winds do not produce high amplitude waves (but still a lot of mini wavelets). If you're a wind surfer looking at that from your window on top of the hill, your heart is going to skip a beat and your next move is to call Dave "Man! gear up. Meet you in five on the water!"
Swell
This is you looking from the bridge of your boat on the morning, after having battled with the storm all night. The storm has dissipated and the long large waves are the last witness of what was definitely a shaky night (people with sailing experience will know ...).
T-Storm
And this was what you were up to the night before...
second gif done at home, hence the lack of detail ... sorry
To the bottom:
Finally, the gui will let you add a patch around the water domain. In the gui it is transparent so you could add objects underwater or a nice ocean bottom. Unfortunately, the GIF format cannot include an alpha channel so no transparency here (but if you export in a video then you should be ok).
Moreover, the export to GIF degrade the image, the joint between the domain border and the water surface is flawless if you run that in Matlab. In some case it also make Matlab degrade the rendering of the lighting, so this is definitely not the best option for export, but it allows more things to play within matlab.
Now onto the code:
Instead of listing the full GUI, which would be super long (this post is long enough already), I will just list here the re-written version of your code, and explain the changes.
You should notice a massive increase of speed execution (orders of magnitude), thanks to the remaining vectorization, but mostly for two reasons:
(i) A lot of calculations were repeated. Caching values and reusing them is much faster than recalculating full matrices in loops (during the animation part).
(ii) Note how I defined the surface graphic object. It is defined only once (empty even), then all the further calls (in the loop) only update the underlying ZData of the surface object (instead of re-creating a surface object at each iteration.
Here goes:
%% // clear workspace
clear all; close all; clc;
%% // Default parameters
param.meshsize = 128 ; %// main grid size
param.patchsize = 200 ;
param.windSpeed = 100 ; %// what unit ? [m/s] ??
param.winddir = 90 ; %// Azimuth
param.rng = 13 ; %// setting seed for random numbers
param.A = 1e-7 ; %// Scaling factor
param.g = 9.81 ; %// gravitational constant
param.xLim = [-10 10] ; %// domain limits X
param.yLim = [-10 10] ; %// domain limits Y
param.zLim = [-1e-4 1e-4]*2 ;
gridSize = param.meshsize * [1 1] ;
%% // Define the grid X-Y domain
x = linspace( param.xLim(1) , param.xLim(2) , param.meshsize ) ;
y = linspace( param.yLim(1) , param.yLim(2) , param.meshsize ) ;
[X,Y] = meshgrid(x, y);
%% // get the grid parameters which remain constants (not time dependent)
[H0, W, Grid_Sign] = initialize_wave( param ) ;
%% // calculate wave at t0
t0 = 0 ;
Z = calc_wave( H0 , W , t0 , Grid_Sign ) ;
%% // populate the display panel
h.fig = figure('Color','w') ;
h.ax = handle(axes) ; %// create an empty axes that fills the figure
h.surf = handle( surf( NaN(2) ) ) ; %// create an empty "surface" object
%% // Display the initial wave surface
set( h.surf , 'XData',X , 'YData',Y , 'ZData',Z )
set( h.ax , 'XLim',param.xLim , 'YLim',param.yLim , 'ZLim',param.zLim )
%% // Change some rendering options
axis off %// make the axis grid and border invisible
shading interp %// improve shading (remove "faceted" effect)
blue = linspace(0.4, 1.0, 25).' ; cmap = [blue*0, blue*0, blue]; %'// create blue colormap
colormap(cmap)
%// configure lighting
h.light_handle = lightangle(-45,30) ; %// add a light source
set(h.surf,'FaceLighting','phong','AmbientStrength',.3,'DiffuseStrength',.8,'SpecularStrength',.9,'SpecularExponent',25,'BackFaceLighting','unlit')
%% // Animate
view(75,55) %// no need to reset the view inside the loop ;)
timeStep = 1./25 ;
nSteps = 2000 ;
for time = (1:nSteps)*timeStep
%// update wave surface
Z = calc_wave( H0,W,time,Grid_Sign ) ;
h.surf.ZData = Z ;
pause(0.001);
end
%% // This block of code is only if you want to generate a GIF file
%// be carefull on how many frames you put there, the size of the GIF can
%// quickly grow out of proportion ;)
nFrame = 55 ;
gifFileName = 'MyDancingWaves.gif' ;
view(-70,40)
clear im
f = getframe;
[im,map] = rgb2ind(f.cdata,256,'nodither');
im(1,1,1,20) = 0;
iframe = 0 ;
for time = (1:nFrame)*.5
%// update wave surface
Z = calc_wave( H0,W,time,Grid_Sign ) ;
h.surf.ZData = Z ;
pause(0.001);
f = getframe;
iframe= iframe+1 ;
im(:,:,1,iframe) = rgb2ind(f.cdata,map,'nodither');
end
imwrite(im,map,gifFileName,'DelayTime',0,'LoopCount',inf)
disp([num2str(nFrame) ' frames written in file: ' gifFileName])
You'll notice that I changed a few things, but I can assure you the calculations are exactly the same. This code calls a few subfunctions but they are all vectorized so if you want you can just copy/paste them here and run everything inline.
The first function called is initialize_wave.m
Everything calculated here will be constant later (it does not vary with time when you later animate the waves), so it made sense to put that into a block on it's own.
function [H0, W, Grid_Sign] = initialize_wave( param )
% function [H0, W, Grid_Sign] = initialize_wave( param )
%
% This function return the wave height coefficients H0 and W for the
% parameters given in input. These coefficients are constants for a given
% set of input parameters.
% Third output parameter is optional (easy to recalculate anyway)
rng(param.rng); %// setting seed for random numbers
gridSize = param.meshsize * [1 1] ;
meshLim = pi * param.meshsize / param.patchsize ;
N = linspace(-meshLim , meshLim , param.meshsize ) ;
M = linspace(-meshLim , meshLim , param.meshsize ) ;
[Kx,Ky] = meshgrid(N,M) ;
K = sqrt(Kx.^2 + Ky.^2); %// ||K||
W = sqrt(K .* param.g); %// deep water frequencies (empirical parameter)
[windx , windy] = pol2cart( deg2rad(param.winddir) , 1) ;
P = phillips(Kx, Ky, [windx , windy], param.windSpeed, param.A, param.g) ;
H0 = 1/sqrt(2) .* (randn(gridSize) + 1i .* randn(gridSize)) .* sqrt(P); % height field at time t = 0
if nargout == 3
Grid_Sign = signGrid( param.meshsize ) ;
end
Note that the initial winDir parameter is now expressed with a single scalar value representing the "azimuth" (in degrees) of the wind (anything from 0 to 360). It is later translated to its X and Y components thanks to the function pol2cart.
[windx , windy] = pol2cart( deg2rad(param.winddir) , 1) ;
This insure that the norm is always 1.
The function calls your problematic phillips.m separately, but as said before it works even fully vectorized so you can copy it back inline if you like. (don't worry I checked the results against your versions => strictly identical). Note that this function does not output complex numbers so there was no need to compare the imaginary parts.
function P = phillips(Kx, Ky, windDir, windSpeed, A, g)
%// The function now accept scalar, vector or full 2D grid matrix as input
K_sq = Kx.^2 + Ky.^2;
L = windSpeed.^2 ./ g;
k_norm = sqrt(K_sq) ;
WK = Kx./k_norm * windDir(1) + Ky./k_norm * windDir(2);
P = A ./ K_sq.^2 .* exp(-1.0 ./ (K_sq * L^2)) .* WK.^2 ;
P( K_sq==0 | WK<0 ) = 0 ;
end
The next function called by the main program is calc_wave.m. This function finishes the calculations of the wave field for a given time. It is definitely worth having that on its own because this is the mimimun set of calculations which will have to be repeated for each given time when you want to animate the waves.
function Z = calc_wave( H0,W,time,Grid_Sign )
% Z = calc_wave( H0,W,time,Grid_Sign )
%
% This function calculate the wave height based on the wave coefficients H0
% and W, for a given "time". Default time=0 if not supplied.
% Fourth output parameter is optional (easy to recalculate anyway)
% recalculate the grid sign if not supplied in input
if nargin < 4
Grid_Sign = signGrid( param.meshsize ) ;
end
% Assign time=0 if not specified in input
if nargin < 3 ; time = 0 ; end
wt = exp(1i .* W .* time ) ;
Ht = H0 .* wt + conj(rot90(H0,2)) .* conj(wt) ;
Z = real( ifft2(Ht) .* Grid_Sign ) ;
end
The last 3 lines of calculations require a bit of explanation as they received the biggest changes (all for the same result but a much better speed).
Your original line:
Ht = H0 .* exp(1i .* W .* (t * timeStep)) + conj(flip(flip(H0,1),2)) .* exp(-1i .* W .* (t * timeStep));
recalculate the same thing too many times to be efficient:
(t * timeStep) is calculated twice on the line, at each loop, while it is easy to get the proper time value for each line when time is initialised at the beginning of the loop for time = (1:nSteps)*timeStep.
Also note that exp(-1i .* W .* time) is the same than conj(exp(1i .* W .* time)). Instead of doing 2*m*n multiplications to calculate them each, it is faster to calculate one once, then use the conj() operation which is much faster.
So your single line would become:
wt = exp(1i .* W .* time ) ;
Ht = H0 .* wt + conj(flip(flip(H0,1),2)) .* conj(wt) ;
Last minor touch, flip(flip(H0,1),2)) can be replaced by rot90(H0,2) (also marginally faster).
Note that because the function calc_wave is going to be repeated extensively, it is definitely worth reducing the number of calculations (as we did above), but also by sending it the Grid_Sign parameter (instead of letting the function recalculate it every iteration). This is why:
Your mysterious function signCor(ifft2(Ht),meshSize)), simply reverse the sign of every other element of Ht. There is a faster way of achieving that: simply multiply Ht by a matrix the same size (Grid_Sign) which is a matrix of alternated +1 -1 ... and so on.
so signCor(ifft2(Ht),meshSize) becomes ifft2(Ht) .* Grid_Sign.
Since Grid_Sign is only dependent on the matrix size, it does not change for each time in the loop, you only calculate it once (before the loop) then use it as it is for every other iteration. It is calculated as follow (vectorized, so you can also put it inline in your code):
function sgn = signGrid(n)
% return a matrix the size of n with alternate sign for every indice
% ex: sgn = signGrid(3) ;
% sgn =
% -1 1 -1
% 1 -1 1
% -1 1 -1
[x,y] = meshgrid(1:n,1:n) ;
sgn = ones( n ) ;
sgn(mod(x+y,2)==0) = -1 ;
end
Lastly, you will notice a difference in how the grids [Kx,Ky] are defined between your version and this one. They do produce slightly different result, it's just a matter of choice.
To explain with a simple example, let's consider a small meshsize=5. Your way of doing things will split that into 5 values, equally spaced, like so:
Kx(first line)=[-1.5 -0.5 0.5 1.5 2.5] * 2 * pi / patchSize
while my way of producing the grid will produce equally spaced values, but also centered on the domain limits, like so:
Kx(first line)=[-2.50 -1.25 0.0 1.25 2.50] * 2 * pi / patchSize
It seems to respect more your comment % = 2*pi*n / Lx, -N/2 <= n < N/2 on the line where you define it.
I tend to prefer symmetric solutions (plus it is also slightly faster but it is only calculated once so it is not a big deal), so I used my vectorized way, but it is purely a matter of choice, you can definitely keep your way, it only ever so slightly "offset" the whole result matrix, but it doesn't perturbate the calculations per se.
last remains of the first answer
Side programming notes:
I detect you come from the C/C++ world or family. In Matlab you do not need to define decimal number with a coma (like 2.0, you used that for most of your numbers). Unless specifically defined otherwise, Matlab by default cast any number to double, which is a 64 bit floating point type. So writing 2 * pi is enough to get the maximum precision (Matlab won't cast pi as an integer ;-)), you do not need to write 2.0 * pi. Although it will still work if you don't want to change your habits.
Also, (one of the great benefit of Matlab), adding . before an operator usually mean "element-wise" operation. You can add (.+), substract (.-), multiply (.*), divide (./) full matrix element wise this way. This is how I got rid of all the loops in your code. This also work for the power operator: A.^2 will return a matrix the same size as A with every element squared.
Here's the working program.
First of all - source code:
clear all; close all; clc;
rng(13); % setting seed for random numbers
meshSize = 128; % field size
windDir = [0.1,1];
patchSize = 200;
A = 1e-7;
g = 9.81; % gravitational constant
windSpeed = 100;
timeStep = 1/25;
x1 = linspace(-10, 10, meshSize+1); x = x1(1:meshSize);
y1 = linspace(-10, 10, meshSize+1); y = y1(1:meshSize);
[X,Y] = meshgrid(x,y); % wave field
i = 1:meshSize; j = 1:meshSize; % indecies
[I,J] = meshgrid(i,j); % field of indecies
Kx = 2.0 * pi / patchSize * (-meshSize / 2.0 + I); % = 2*pi*n / Lx, -N/2 <= n < N/2
Ky = 2.0 * pi / patchSize * (-meshSize / 2.0 + J); % = 2*pi*m / Ly, -M/2 <= m < M/2
K = sqrt(Kx.^2 + Ky.^2); % ||K||
W = sqrt(K .* g); % deep water frequencies (empirical parameter)
P = zeros(size(X)); % Cant compute P without loops
for i = 1:meshSize
for j = 1:meshSize
P(i,j) = phillips(Kx(i,j), Ky(i,j), windDir, windSpeed, A, g); % phillips spectrum
end
end
H0 = 1/sqrt(2) .* (randn(size(X)) + 1i .* randn(size(X))) .* sqrt(P); % height field at time t = 0
rotate3d on;
for t = 1:10000 % 10000 * timeStep (sec)
Ht = H0 .* exp(1i .* W .* (t * timeStep)) + ...
conj(flip(flip(H0,1),2)) .* exp(-1i .* W .* (t * timeStep));
[az,el] = view;
surf(X,Y,real(signCor(ifft2(Ht),meshSize)));
axis([-10 10 -10 10 -1e-4 1e-4]); view(az,el);
blue = linspace(0.4, 1.0, 25)'; map = [blue*0, blue*0, blue];
%shading interp; % improve shading (remove "faceted" effect)
colormap(map);
pause(1/60);
end
phillips.m: (I've tried to vectorize the computation of Phillips spectrum but I faced with a difficulty which I'll show further)
function P = phillips(kx, ky, windDir, windSpeed, A, g)
k_sq = kx^2 + ky^2;
if k_sq == 0
P = 0;
else
L = windSpeed^2 / g;
k = [kx, ky] / sqrt(k_sq);
wk = k(1) * windDir(1) + k(2) * windDir(2);
P = A / k_sq^2 * exp(-1.0 / (k_sq * L^2)) * wk^2;
if wk < 0
P = 0;
end
end
end
signCor.m: (This function is an absolutely mystery for me... I've copied it from "CUDA FFT Ocean Simulation" realization. Simulation works much worse without it. And again I don't know how to vectorize this function.)
function H = signCor(H1, meshSize)
H = H1;
for i = 1:meshSize
for j = 1:meshSize
if mod(i+j,2) == 0
sign = -1; % works fine if we change signs vice versa
else
sign = 1;
end
H(i,j) = H1(i,j) * sign;
end
end
end
The biggest mistake that I've done is that I used ifft instead of using ifft2, that's why CUDA ifft and Matlab ifft didn't match.
My second mistake was in this lines of code:
kx = 2.0 * pi / patchSize * (-meshSize / 2.0 + x(i)); % = 2*pi*n / Lx
ky = 2.0 * pi / patchSize * (-meshSize / 2.0 + y(j)); % = 2*pi*m / Ly
I should've write:
kx = 2.0 * pi / patchSize * (-meshSize / 2.0 + i); % = 2*pi*n / Lx
ky = 2.0 * pi / patchSize * (-meshSize / 2.0 + j); % = 2*pi*m / Ly
I've played a bit with parameters A, meshSize, patchSize and I came to the conclusion that:
Somehow plausible parameter of wave amplitude is A * (patchSize / meshSize), where A is nothing but a scaling factor.
For 'calm' patchSize / meshSize <= 0.5.
For 'tsunami' patchSize / meshSize >= 3.0.
Difficulty with a vectorization of Phillips spectrum:
I have 2 functions:
% non-vectorized spectrum
function P = phillips1(kx, ky, windDir, windSpeed, A, g)
k_sq = kx^2 + ky^2;
if k_sq == 0
P = 0;
else
L = windSpeed^2 / g;
k = [kx, ky] / sqrt(k_sq);
wk = k(1) * windDir(1) + k(2) * windDir(2);
P = A / k_sq^2 * exp(-1.0 / (k_sq * L^2)) * wk^2;
if wk < 0
P = 0;
end
end
end
% vectorized spectrum
function P = phillips2(Kx, Ky, windDir, windSpeed, A, g)
K_sq = Kx .^ 2 + Ky .^ 2;
L = -g^2 / windSpeed^4;
WK = (Kx ./ K_sq) .* windDir(1) + (Ky ./ K_sq) .* windDir(2);
P = (A ./ (K_sq .^ 2)) .* ( exp(L ./ K_sq) .* (WK .^ 2) );
P(K_sq == 0) = 0;
P(WK < 0) = 0;
P(isinf(P)) = 0;
end
After I compute P1 using phillips1 and P2 using phillips2 I plot their difference:
subplot(2,1,1); surf(X,Y,real(P2-P1)); title('Difference in real part');
subplot(2,1,2); surf(X,Y,imag(P2-P1)); title('Difference in imaginary part');
It perfectly illustrates that there's a huge difference between this 2 spectrums in real part.

Neural Networks: Sigmoid Activation Function for continuous output variable

Okay, so I am in the middle of Andrew Ng's machine learning course on coursera and would like to adapt the neural network which was completed as part of assignment 4.
In particular, the neural network which I had completed correctly as part of the assignment was as follows:
Sigmoid activation function: g(z) = 1/(1+e^(-z))
10 output units, each which could take 0 or 1
1 hidden layer
Back-propagation method used to minimize cost function
Cost function:
where L=number of layers, s_l = number of units in layer l, m = number of training examples, K = number of output units
Now I want to adjust the exercise so that there is one continuous output unit that takes any value between [0,1] and I am trying to work out what needs to change, so far I have
Replaced the data with my own, i.e.,such that the output is continuous variable between 0 and 1
Updated references to the number of output units
Updated the cost function in the back-propagation algorithm to:
where a_3 is the value of the output unit determined from forward propagation.
I am certain that something else must change as the gradient checking method shows the gradient determined by back-propagation and that by the numerical approximation no longer match up. I did not change the sigmoid gradient; it is left at f(z)*(1-f(z)) where f(z) is the sigmoid function 1/(1+e^(-z))) nor did I update the numerical approximation of the derivative formula; simply (J(theta+e) - J(theta-e))/(2e).
Can anyone advise of what other steps would be required?
Coded in Matlab as follows:
% FORWARD PROPAGATION
% input layer
a1 = [ones(m,1),X];
% hidden layer
z2 = a1*Theta1';
a2 = sigmoid(z2);
a2 = [ones(m,1),a2];
% output layer
z3 = a2*Theta2';
a3 = sigmoid(z3);
% BACKWARD PROPAGATION
delta3 = a3 - y;
delta2 = delta3*Theta2(:,2:end).*sigmoidGradient(z2);
Theta1_grad = (delta2'*a1)/m;
Theta2_grad = (delta3'*a2)/m;
% COST FUNCTION
J = 1/(2 * m) * sum( (a3-y).^2 );
% Implement regularization with the cost function and gradients.
Theta1_grad(:,2:end) = Theta1_grad(:,2:end) + Theta1(:,2:end)*lambda/m;
Theta2_grad(:,2:end) = Theta2_grad(:,2:end) + Theta2(:,2:end)*lambda/m;
J = J + lambda/(2*m)*( sum(sum(Theta1(:,2:end).^2)) + sum(sum(Theta2(:,2:end).^2)));
I have since realised that this question is similar to that asked by #Mikhail Erofeev on StackOverflow, however in this case I wish the continuous variable to be between 0 and 1 and therefore use a sigmoid function.
First, your cost function should be:
J = 1/m * sum( (a3-y).^2 );
I think your Theta2_grad = (delta3'*a2)/m;is expected to match the numerical approximation after changed to delta3 = 1/2 * (a3 - y);).
Check this slide for more details.
EDIT:
In case there is some minor discrepancy between our codes, I pasted my code below for your reference. The code has already been compared with numerical approximation function checkNNGradients(lambda);, the Relative Difference is less than 1e-4 (not meets the 1e-11 requirement by Dr.Andrew Ng though)
function [J grad] = nnCostFunctionRegression(nn_params, ...
input_layer_size, ...
hidden_layer_size, ...
num_labels, ...
X, y, lambda)
Theta1 = reshape(nn_params(1:hidden_layer_size * (input_layer_size + 1)), ...
hidden_layer_size, (input_layer_size + 1));
Theta2 = reshape(nn_params((1 + (hidden_layer_size * (input_layer_size + 1))):end), ...
num_labels, (hidden_layer_size + 1));
m = size(X, 1);
J = 0;
Theta1_grad = zeros(size(Theta1));
Theta2_grad = zeros(size(Theta2));
X = [ones(m, 1) X];
z1 = sigmoid(X * Theta1');
zs = z1;
z1 = [ones(m, 1) z1];
z2 = z1 * Theta2';
ht = sigmoid(z2);
y_recode = zeros(length(y),num_labels);
for i=1:length(y)
y_recode(i,y(i))=1;
end
y = y_recode;
regularization=lambda/2/m*(sum(sum(Theta1(:,2:end).^2))+sum(sum(Theta2(:,2:end).^2)));
J=1/(m)*sum(sum((ht - y).^2))+regularization;
delta_3 = 1/2*(ht - y);
delta_2 = delta_3 * Theta2(:,2:end) .* sigmoidGradient(X * Theta1');
delta_cap2 = delta_3' * z1;
delta_cap1 = delta_2' * X;
Theta1_grad = ((1/m) * delta_cap1)+ ((lambda/m) * (Theta1));
Theta2_grad = ((1/m) * delta_cap2)+ ((lambda/m) * (Theta2));
Theta1_grad(:,1) = Theta1_grad(:,1)-((lambda/m) * (Theta1(:,1)));
Theta2_grad(:,1) = Theta2_grad(:,1)-((lambda/m) * (Theta2(:,1)));
grad = [Theta1_grad(:) ; Theta2_grad(:)];
end
If you want to have continuous output try not to use sigmoid activation when computing target value.
a1 = [ones(m, 1) X];
a2 = sigmoid(X * Theta1');
a2 = [ones(m, 1) z1];
a3 = z1 * Theta2';
ht = a3;
Normalize input before using it in nnCostFunction. Everything else remains same.

Octave backpropagation implementation issues

I wrote a code to implement steepest descent backpropagation with which I am having issues. I am using the Machine CPU dataset and have scaled the inputs and outputs into range [0 1]
The codes in matlab/octave is as follows:
steepest descent backpropagation
%SGD = Steepest Gradient Decent
function weights = nnSGDTrain (X, y, nhid_units, gamma, max_epoch, X_test, y_test)
iput_units = columns (X);
oput_units = columns (y);
n = rows (X);
W2 = rand (nhid_units + 1, oput_units);
W1 = rand (iput_units + 1, nhid_units);
train_rmse = zeros (1, max_epoch);
test_rmse = zeros (1, max_epoch);
for (epoch = 1:max_epoch)
delW2 = zeros (nhid_units + 1, oput_units)';
delW1 = zeros (iput_units + 1, nhid_units)';
for (i = 1:rows(X))
o1 = sigmoid ([X(i,:), 1] * W1); %1xn+1 * n+1xk = 1xk
o2 = sigmoid ([o1, 1] * W2); %1xk+1 * k+1xm = 1xm
D2 = o2 .* (1 - o2);
D1 = o1 .* (1 - o1);
e = (y_test(i,:) - o2)';
delta2 = diag (D2) * e; %mxm * mx1 = mx1
delta1 = diag (D1) * W2(1:(end-1),:) * delta2; %kxm * mx1 = kx1
delW2 = delW2 + (delta2 * [o1 1]); %mx1 * 1xk+1 = mxk+1 %already transposed
delW1 = delW1 + (delta1 * [X(i, :) 1]); %kx1 * 1xn+1 = k*n+1 %already transposed
end
delW2 = gamma .* delW2 ./ n;
delW1 = gamma .* delW1 ./ n;
W2 = W2 + delW2';
W1 = W1 + delW1';
[dummy train_rmse(epoch)] = nnPredict (X, y, nhid_units, [W1(:);W2(:)]);
[dummy test_rmse(epoch)] = nnPredict (X_test, y_test, nhid_units, [W1(:);W2(:)]);
printf ('Epoch: %d\tTrain Error: %f\tTest Error: %f\n', epoch, train_rmse(epoch), test_rmse(epoch));
fflush (stdout);
end
weights = [W1(:);W2(:)];
% plot (1:max_epoch, test_rmse, 1);
% hold on;
plot (1:max_epoch, train_rmse(1:end), 2);
% hold off;
end
predict
%Now SFNN Only
function [o1 rmse] = nnPredict (X, y, nhid_units, weights)
iput_units = columns (X);
oput_units = columns (y);
n = rows (X);
W1 = reshape (weights(1:((iput_units + 1) * nhid_units),1), iput_units + 1, nhid_units);
W2 = reshape (weights((((iput_units + 1) * nhid_units) + 1):end,1), nhid_units + 1, oput_units);
o1 = sigmoid ([X ones(n,1)] * W1); %nxiput_units+1 * iput_units+1xnhid_units = nxnhid_units
o2 = sigmoid ([o1 ones(n,1)] * W2); %nxnhid_units+1 * nhid_units+1xoput_units = nxoput_units
rmse = RMSE (y, o2);
end
RMSE function
function rmse = RMSE (a1, a2)
rmse = sqrt (sum (sum ((a1 - a2).^2))/rows(a1));
end
I have also trained the same dataset using the R RSNNS package mlp and the RMSE for train set (first 100 examples) are around 0.03 . But in my implementation I cannot achieve lower RMSE than 0.14 . And sometimes the errors grow for some higher learning rates, and no learning rate gets me lower RMSE than 0.14. Also a paper i referred report the RMSE in for the train set is around 0.03
I wanted to know where is the problem i the code. I have followed Raul Rojas book and confirmed that things are okay.
In backprobagation code the line
e = (y_test(i,:) - o2)';
is not correct, because the o2 is the output from the train set and i am finding the difference from one example from the test set y_test. The line should have been as below:
e = (y(i,:) - o2)';
which correctly finds the difference between the predicted output by the current model and the target output of the corresponding example.
This took me 3 days to find this one, I am fortunate enough to find this freaking bug which stopped me from going into further modifications.