I am an Engineer with Engineering Development Group at Mathworks.

My area of interest includes Deep Learning and Machine Learning.

DISCLAIMER: Any advice or opinion here are my own and in no way reflect that of MathWorks.

Answered

Solving second-order non-linear PDE

As per my understanding, the core issue here is with the variable k which needs to be saturated. In other words, k = min(0, max...

Solving second-order non-linear PDE

As per my understanding, the core issue here is with the variable k which needs to be saturated. In other words, k = min(0, max...

3 days ago | 0

Answered

Why is dual boot installation not working?

For any installation related help, contact MathWorks support via the contact us page.

Why is dual boot installation not working?

For any installation related help, contact MathWorks support via the contact us page.

3 days ago | 0

| accepted

Answered

Increasing the number of iterations in GeneralizedLinearModel.fit

As per my understanding, you want to get the p values from the fitted model. You can use fitglm for this purpose. You can increa...

Increasing the number of iterations in GeneralizedLinearModel.fit

As per my understanding, you want to get the p values from the fitted model. You can use fitglm for this purpose. You can increa...

3 days ago | 0

Answered

Simulink does not work (Ubuntu 20.04)

This might happen due to installation issues. It looks like some files are missing. Reinstall MATLAB, and disable antivirus soft...

Simulink does not work (Ubuntu 20.04)

This might happen due to installation issues. It looks like some files are missing. Reinstall MATLAB, and disable antivirus soft...

3 days ago | 0

Answered

Help with a vectorizing: rearranging a matrix

Assuming F itself can be vectorized, first calculate all required values of F. len = 5; F = randi(len, [len, len]); % Replace ...

Help with a vectorizing: rearranging a matrix

Assuming F itself can be vectorized, first calculate all required values of F. len = 5; F = randi(len, [len, len]); % Replace ...

3 days ago | 0

Answered

Have a Problem using CONV2

The plot function requires both arguments to be of same size. While the solution depends on the nature of the data, the most li...

Have a Problem using CONV2

The plot function requires both arguments to be of same size. While the solution depends on the nature of the data, the most li...

4 days ago | 0

Answered

Unrecognized function or variable 'fitrnet'.

fitrnet was introduced in R2021a. Ensure you have the correct release installed, and that you have the statistics and machine le...

Unrecognized function or variable 'fitrnet'.

fitrnet was introduced in R2021a. Ensure you have the correct release installed, and that you have the statistics and machine le...

4 days ago | 0

Answered

Calculating principal component scores from principal component coefficients of the new data

To get the scores for new data, you need to first get the outputs mu and coeff. X = rand(100, 5); XTrain = X(1:75, :) XTest =...

Calculating principal component scores from principal component coefficients of the new data

To get the scores for new data, you need to first get the outputs mu and coeff. X = rand(100, 5); XTrain = X(1:75, :) XTest =...

4 days ago | 0

| accepted

Answered

speeding up trainbr using more cpu cores or a gpu

Bayesian regularization requires calculating the Jacobian. Jacobian calculation is not supported on GPU. Hence trainbr doesn't s...

speeding up trainbr using more cpu cores or a gpu

Bayesian regularization requires calculating the Jacobian. Jacobian calculation is not supported on GPU. Hence trainbr doesn't s...

5 days ago | 0

Answered

Low accuracy of CNN

You can use all the data by passing some data at a time, also called as a MiniBatch. See the MiniBatchSize option in traningopti...

Low accuracy of CNN

You can use all the data by passing some data at a time, also called as a MiniBatch. See the MiniBatchSize option in traningopti...

5 days ago | 0

Answered

Function 'fmincon' not supported for code generation

fmincon codegen support was added in R2019b. Also, optimOptions is the last argument for fmincon, you should pass other argument...

Function 'fmincon' not supported for code generation

fmincon codegen support was added in R2019b. Also, optimOptions is the last argument for fmincon, you should pass other argument...

5 days ago | 1

| accepted

Answered

Some CNN architecture are working, other are not

As some of the models are working, but others are not, the issue is likely with the training options used while transfer learnin...

Some CNN architecture are working, other are not

As some of the models are working, but others are not, the issue is likely with the training options used while transfer learnin...

5 days ago | 1

| accepted

Answered

Why do I have the same validation accuracy for every epoch?

As per my understanding, the data you have in unidimensional, and is time variant. It might be a better option to consider this...

Why do I have the same validation accuracy for every epoch?

As per my understanding, the data you have in unidimensional, and is time variant. It might be a better option to consider this...

6 days ago | 0

Answered

Random forest prediction probabilities

Getting a probability of 1 suggests that the model has overfitted, and the observation is being predicted as belonging to the sp...

Random forest prediction probabilities

Getting a probability of 1 suggests that the model has overfitted, and the observation is being predicted as belonging to the sp...

6 days ago | 0

Answered

How to re-train a neural network

Check the documentation on how to resume training from checkpoint. In short, save the model to a mat file using the CheckpointP...

How to re-train a neural network

Check the documentation on how to resume training from checkpoint. In short, save the model to a mat file using the CheckpointP...

6 days ago | 0

Answered

How to create a matrix with all possibles cambinations between nodes of 3 sets?

You can use meshgrid function as below [x,y,z] = meshgrid(C,O,P); This gives you all combinations of C/O/P.

How to create a matrix with all possibles cambinations between nodes of 3 sets?

You can use meshgrid function as below [x,y,z] = meshgrid(C,O,P); This gives you all combinations of C/O/P.

1 month ago | 0

Answered

Clustering of 1d array data set

You can use dbscan on 1d array, as below X = rand(100,1); dbscan(X, 0.1, 5) However, it might not be the most appropriate one...

Clustering of 1d array data set

You can use dbscan on 1d array, as below X = rand(100,1); dbscan(X, 0.1, 5) However, it might not be the most appropriate one...

1 month ago | 0

Answered

Number of leaf nodes used by regression tree

The IsBranchNode Property of RegressionTree is false for leaf nodes. So you can use it as follows, X = rand(100, 4); y = rand(...

Number of leaf nodes used by regression tree

The IsBranchNode Property of RegressionTree is false for leaf nodes. So you can use it as follows, X = rand(100, 4); y = rand(...

1 month ago | 0

Answered

Calculating std and 95% confidence intervals in a 3d matrix along the 3rd dimension

std(std(M)) would give you std deviations of the std deviations, which I assume is not what you are expecting. If you want std d...

Calculating std and 95% confidence intervals in a 3d matrix along the 3rd dimension

std(std(M)) would give you std deviations of the std deviations, which I assume is not what you are expecting. If you want std d...

1 month ago | 0

Answered

Rank on symbolic matrices

Rank does not take identities satisfied by functions into account. As a workaround, substitute values into variables, and then c...

Rank on symbolic matrices

Rank does not take identities satisfied by functions into account. As a workaround, substitute values into variables, and then c...

1 month ago | 0

Answered

Classification Learner multi labels

Multi class classification can be considered as a regression problem, where the model predicts the probability of each of the cl...

Classification Learner multi labels

Multi class classification can be considered as a regression problem, where the model predicts the probability of each of the cl...

1 month ago | 0

Answered

Question regarding this link: https://www.mathworks.com/matlabcentral/answers/495218-what-is-the-error-histogram-in-neural-network-matlab

The histogram is created from the error in the output. error = targets - outputs; number_of_bins = 10; ploterrhist(error,'bi...

Question regarding this link: https://www.mathworks.com/matlabcentral/answers/495218-what-is-the-error-histogram-in-neural-network-matlab

The histogram is created from the error in the output. error = targets - outputs; number_of_bins = 10; ploterrhist(error,'bi...

1 month ago | 0

Answered

Why does the RL Toolbox not support BatchNormalization layer?

This is an known issue, and it might be fixed in any of the upcoming releases.

Why does the RL Toolbox not support BatchNormalization layer?

This is an known issue, and it might be fixed in any of the upcoming releases.

1 month ago | 0

| accepted

Answered

fitrgp with censored data

fitrgp currently does not support censored data. This might be implemented in any of the future releases. As a workaround, you ...

fitrgp with censored data

fitrgp currently does not support censored data. This might be implemented in any of the future releases. As a workaround, you ...

1 month ago | 0

Answered

Find random solutions of a system of inequalities

As the solutions are infinite, you can get solutions as a system of equations themselves. Then, you can either randomly put para...

Find random solutions of a system of inequalities

As the solutions are infinite, you can get solutions as a system of equations themselves. Then, you can either randomly put para...

1 month ago | 0

| accepted

Answered

Kernel function interpretation problem

As ksdensity returns the probability density, it can be higher than one. The integral of this function, which is the total proba...

Kernel function interpretation problem

As ksdensity returns the probability density, it can be higher than one. The integral of this function, which is the total proba...

1 month ago | 0

| accepted

Answered

My Neural Net Pattern recognition confusion matrix result is 96% but when I add new input the output of net show always same result. I didn't understand why .

If neural network has issues with specific classes/outputs, then you should check if that specific class has very few samples in...

My Neural Net Pattern recognition confusion matrix result is 96% but when I add new input the output of net show always same result. I didn't understand why .

If neural network has issues with specific classes/outputs, then you should check if that specific class has very few samples in...

1 month ago | 0

Answered

Huge Confidence Interval With predint

As per my understanding, you want to get a fit with lower confidence interval. For this, you need to do one or more of the foll...

Huge Confidence Interval With predint

As per my understanding, you want to get a fit with lower confidence interval. For this, you need to do one or more of the foll...

2 months ago | 0

Answered

Image regression: How to visualize the feature importance of an image in convolutional neural networks

the third parameter for occlusionSensitivity is label which was predicted for the model. For example, label = classify(net,X); ...

Image regression: How to visualize the feature importance of an image in convolutional neural networks

the third parameter for occlusionSensitivity is label which was predicted for the model. For example, label = classify(net,X); ...

2 months ago | 0

Answered

I can not open it

I assume that you are facing this issue after installation or upgrade. If so, you can reach out to customer support for help wit...

I can not open it

I assume that you are facing this issue after installation or upgrade. If so, you can reach out to customer support for help wit...

2 months ago | 0