The following is a Matlab code. I am getting too big of an error. The max error should be less than 1*10^-3. I think its because of the backslash operator I used here, X = A \ b. I can't do X = A * inv(b) because b is not a square matrix. How should I reduce the error? Also, I need to do this without Symbolic computation. % Problem 1 % Step 1: Compute the right-hand side vector b n = 20; Xo = ones(n, 1); % Column vector with ones in each component A = zeros(n); % Initialize the matrix A for i = 1:n for j = 1:n A(i, j) = 1 / (i + j - 1); end end b = A * Xo; % Step 2: Solve the system AX = b numerically X = A \ b; % Backslash operator for numerical solution % Step 3: Compute the error vector E and find the maximum component E = X - Xo; E_inf = max(abs(E));
The following is a Matlab code. I am getting too big of an error. The max error should be less than 1*10^-3. I think its because of the backslash operator I used here, X = A \ b. I can't do X = A * inv(b) because b is not a square matrix. How should I reduce the error? Also, I need to do this without Symbolic computation.
% Problem 1
% Step 1: Compute the right-hand side
n = 20;
Xo = ones(n, 1); % Column vector with ones in each component
A = zeros(n); % Initialize the matrix A
for i = 1:n
for j = 1:n
A(i, j) = 1 / (i + j - 1);
end
end
b = A * Xo;
% Step 2: Solve the system AX = b numerically
X = A \ b; % Backslash operator for numerical solution
% Step 3: Compute the error vector E and find the maximum component
E = X - Xo;
E_inf = max(abs(E));
Step by step
Solved in 3 steps