Community Profile

photo

Mahesh Taparia


Last seen: 3 days ago

MathWorks

101 total contributions since 2019

I am an Engineer in the Engineering Development Group at Mathworks, Hyderabad.
My area of interest are signal processing, machine learning, deep learning and communication systems.
DISCLAIMER: Any advice here are my own and no way reflect that of the Mathworks.

Mahesh Taparia's Badges

  • Revival Level 1
  • Knowledgeable Level 3
  • 6 Month Streak
  • First Answer

View details...

Contributions in
View by

Answered
How can I see the connection of the hidden layer in CNN?
Hi I think you are asking how the CNN works. Let the size of the feature of the 1st layer is M1XN1XD1. For the second layer, l...

10 days ago | 1

Answered
parameters calculation in cnn
Hi I think, you want to know the network parameters information. First define the network and train with your dataset. You can ...

10 days ago | 0

Answered
deep learning RMSE and loss
Hi The inbuilt trained VDSR model is having a size of 41X41X1. But you can change the input size and retrain the VDSR model. F...

10 days ago | 0

Answered
reinforcement learning toolbox ---fail to train stores saved agents in a MAT-file in the folder
Hi There is in built agent file named rlQuadrupedAgent.mat in MATLAB directory. But there is no file named as Agent512.mat. Yo...

10 days ago | 0

Answered
Classification of cervical cell using deep learning
Hi You can refer to the example on image classification here. Also, you can use several inbuilt model. For more information, re...

10 days ago | 0

Answered
May I use Gaussian Mixture Model after using any method of Dimensionality Reduction?
Hi I think you are asking if GMM can be used after applying the dimension reduction techniques on a dataset. Yes, you can apply...

10 days ago | 0

Answered
trying to do retinal vessel segmentation with mean-c thresholding
Hi You are converting a double image to uint8 format due to which you are unable to visualize the segmentation. Keep in double ...

11 days ago | 0

Answered
Hi i need help trying to extract the name of a value associated to an array
Hi You can create a separate string array with the same elements in the same order and access those with corresponding max ind...

11 days ago | 0

Answered
How can I reduce extract features from a set of Matrices and vectors to be used in Machine Learning
Hi You can vectorised the 3X3 matrix to 9X1, then append with the rest of the features to make the 'd' dimensional input data, ...

11 days ago | 0

Answered
How to get the PI control value by using Bode Plot Method?
Hi You can use 'pidtune' function on transfer function to find the PI value. For example: [C_pi,info] = pidtune(transferFcn,'P...

11 days ago | 0

Answered
Is it possible to have StopTrainingCriteria in rlTrainingOptions ( RL Toolbox )
Hi It can be done by defining the threshold in the training option. For example, set the "AverageReward" as threshold and defi...

11 days ago | 0

Answered
train network error. reshape number of elements must not change. Use [] to automatically calculate the dimension size.
Hi You are having an input of size MxN and you are directly reshaping it to a vector of length 1x1. Before the fullyConnectedLa...

12 days ago | 0

Answered
How to solve equations with functions which contain unknown
Hi If 'As' is a known variable then define in your code and if it is unknown and symbolic variable then define using syms funct...

12 days ago | 0

| accepted

Answered
how can I fit the regression model to a periodic data?
Hi You can use the Curve Fitting Toolbox for this application. There are several possible ways to do that. You can refer to thi...

12 days ago | 0

Answered
Error using vertcat Dimensions of arrays being concatenated are not consistent.
Hi By looking at your code, s = [s; zeros(20*L,1)]; you want to append the rows which consists of zeros. You have mentioned ...

13 days ago | 0

Answered
how to use deep learning with multivariable?
Hi It is not clear what kind of data you are having and what you want to do with that.Explain it. Also confirm whether you are...

13 days ago | 0

Answered
DICOM data as input for Deep Learning
Hi It seems that you are unable to load the mat file into the network. Your input is in mat file format. So, create a custom re...

14 days ago | 0

| accepted

Answered
segmentGroundFromLidarData for pcd file
Hi The input of the function segmentGroundFromLidarData will be a point cloud. You mentioned that your file is having mxn array...

14 days ago | 0

Answered
CNN for video frame prediction
Hi There are some papers based on frame prediction which are using CNN , autoencoder, etc based approach. You can pick anyone o...

2 months ago | 0

Answered
Classification of Leaf Hydration state based on Leaf Colour
Hi You are having very less data to use deep learning, you can use those data at first. Use data augmentation to increase the d...

2 months ago | 0

Answered
Morphological Transformation, remove border border of a closed image
Hi Using morphological operations and connected components algorithm, the problem can be solved with the minor loss of bottom ...

2 months ago | 0

| accepted

Answered
How to export predicted multi-output data from trained neural network?
Hi To predict the model on test data, use 'predict' function instead of 'sim'. For more information, refer to the documentatio...

2 months ago | 0

| accepted

Answered
Single element of Input vector in classifying patterns with a Shallow Neural Network
Hi As per your question, you have a 9 dimensional dataset with a classification of benignitiy or malignancy of breast cancer. ...

2 months ago | 0

Answered
An elman neural network with mulltiple inputs
Hi You can use the elmannet as folllows: net = elmannet(1:3,10); %%% NumDelays=3 [Xs,Xi,Ai,Ts] = preparets(net,X,T); net = ...

2 months ago | 0

Answered
svm training and classification
Hi You can use the function fitcsvm as follows: SVMModel = fitcsvm(xdata,group,'KernelFunction', 'linear'); [label,score] = p...

2 months ago | 0

Answered
Architecture of convolutional autoencoders in Matlab 2019b
Hi You can define custom architecture of auoencoder using deep learning layers. You can refer to this documentation for the li...

2 months ago | 0

| accepted

Answered
adding noise increased accuracy after training
Hi Noise addition acts as regularizer and it reduce overfitting. The model becomes more robust, so the accuracy of the model in...

2 months ago | 0

Answered
Why is the hold on function causing 3 graphs?
Hi Based on the parameters you have specified, the function kutta has been called for three times which resuls in 3 plots insid...

2 months ago | 0

Answered
Deep learning regression network improvements?
Hi By looking at your network design, it seem that you are having input data with dimension of 4 and trying to regress the out...

2 months ago | 0

| accepted

Answered
Reduce the image size while maintaining the quality. Use dct2 with RGB image. when I Concatenate the RGB I get white image
Hi The image get converted to double format, convert back to uint8 format to show correctly. For example: imshow(uint8(rgbIma...

2 months ago | 0

Load more