Hfrxdjt

A strange hotel

Why doesn't the standard consider a template constructor as a copy constructor?

Why do real positive eigenvalues result in an unstable system? What about eigenvalues between 0 and 1? or 1?

Are there moral objections to a life motivated purely by money? How to sway a person from this lifestyle?

What *exactly* is electrical current, voltage, and resistance?

Negative Resistance

A Paper Record is What I Hamper

How much of a wave function must reside inside event horizon for it to be consumed by the black hole?

Extracting Dirichlet series coefficients

Find the identical rows in a matrix

Philosophical question on logistic regression: why isn't the optimal threshold value trained?

Why did C use the -> operator instead of reusing the . operator?

Complex numbers z=-3-4i polar form

Is there a word for the censored part of a video?

How bug prioritization works in agile projects vs non agile

What's the difference between using dependency injection with a container and using a service locator?

"The cow" OR "a cow" OR "cows" in this context

What is the unit of time_lock_delta in LND?

Drawing a german abacus as in the books of Adam Ries

Creating a chemical industry from a medieval tech level without petroleum

Is Diceware more secure than a long passphrase?

A ​Note ​on ​N!

Prove that the countable union of countable sets is also countable

Why do distances seem to matter in the Foundation world?

Calculation of R2 and Mean Square Error for multiple response outputs

Deep Learning: Feed Forward for Unbalanced Classes Using Tensor FlowLearning rate and memory of Least Mean Square algorithmAn Artificial Neuron Network (ANN) with an arbitrary number of inputs and outputsEncog neural network multiple outputsIn a convolutional neural network (CNN), when convolving the image, is the operation used the dot product or the sum of element-wise multiplication?Class leaking on validation setDeep advantage learning: how to predict the valuehow to optimize the weights of a neural net when feeding it with multiple training samples?Wrangling data for CNNKeras NN - Learning a simple formula

0

$begingroup$

My neural network model is 20 inputs and 3 outputs for a regression problem. I am learning how to report the performance or the goodness of fit. http://www.wardsystems.com/manuals/neuroshell2/index.html?rsquared.htm link shows the formula for R2 test. My prediction is a matrix of N by 3 where N is the number of elements.

Question 1) Would R2 be a matrix of 3 by 3 size or a scalar?

Question 2) Calculation of Error_Percentage = (abs(Errors)./Test_Y) * 100; where Errors is also 3 by N. Then would the Mean Absolute Error (MAE) be a scalar given by the formula

MAE = mean(abs(Error_Percentage))

neural-network prediction

share

asked 4 mins ago

Sm1Sm1

11

New contributor

Sm1 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

0

$begingroup$

My neural network model is 20 inputs and 3 outputs for a regression problem. I am learning how to report the performance or the goodness of fit. http://www.wardsystems.com/manuals/neuroshell2/index.html?rsquared.htm link shows the formula for R2 test. My prediction is a matrix of N by 3 where N is the number of elements.

Question 1) Would R2 be a matrix of 3 by 3 size or a scalar?

Question 2) Calculation of Error_Percentage = (abs(Errors)./Test_Y) * 100; where Errors is also 3 by N. Then would the Mean Absolute Error (MAE) be a scalar given by the formula

MAE = mean(abs(Error_Percentage))

neural-network prediction

share

asked 4 mins ago

Sm1Sm1

11

New contributor

Sm1 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

$begingroup$

My neural network model is 20 inputs and 3 outputs for a regression problem. I am learning how to report the performance or the goodness of fit. http://www.wardsystems.com/manuals/neuroshell2/index.html?rsquared.htm link shows the formula for R2 test. My prediction is a matrix of N by 3 where N is the number of elements.

Question 1) Would R2 be a matrix of 3 by 3 size or a scalar?

Question 2) Calculation of Error_Percentage = (abs(Errors)./Test_Y) * 100; where Errors is also 3 by N. Then would the Mean Absolute Error (MAE) be a scalar given by the formula

MAE = mean(abs(Error_Percentage))

neural-network prediction

share

asked 4 mins ago

Sm1Sm1

11

New contributor

Sm1 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

share

asked 4 mins ago

Sm1Sm1

11

New contributor

Sm1 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share

asked 4 mins ago

Sm1Sm1

11

New contributor

Sm1 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 4 mins ago

Sm1Sm1

11

New contributor

Sm1 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 4 mins ago

Sm1Sm1

11