Community Profile # Gautam Pendse

### MathWorks

Last seen: 7 months ago Active since 2014

#### Statistics

• • • #### Content Feed

View by

How can I make my custom convolutional layer (using dlconv) more memory efficient in order to improve the speed of the backward pass?
Hi Julius, One approach that you can try is to rewrite the code like this: ZChannel2 = Z(:, :, :, 2, :); Z2 = dlconv(double(s...

7 months ago | 0

Sampling from Posterior Distribution of GPR Model from fitrgp()
Hi Sterling, Here's an example illustrating how to sample from the posterior distribution of a GPR model. The code uses an un...

10 months ago | 1

| accepted

What is derivative trace in dlgradient function?
Hi Theron, Re: 1. What is derivative trace in dlgradient function? ** Derivative trace is essentially the history containing a...

2 years ago | 2

| accepted

How to Manually Change dlnet's Learnable Parameters?
Hi Theron, The first syntax for dlupdate may be what you are looking for: https://www.mathworks.com/help/deeplearning/ref/dlup...

2 years ago | 0

| accepted

Two Issues about MATLAB's Official Example of GAN
Hi Theron, Re: 2. As I mentioned in another post, the ganLoss(...) function in fact appends a Sigmoid layer at the end of the d...

2 years ago | 1

| accepted

Gaussian process regression Beta values
Hi Sareena, The initial value for 'Beta' is a vector of all zeros. You can specify an initial value using the 'Beta' name/value...

2 years ago | 0

| accepted

Can I use parallel computing when training a gaussian process with separate length scales for predictors with fitgrp?
Hi Lauri, Even when there are separate length scales for predictors, these are jointly optimized during training. This optimi...

3 years ago | 0

| accepted

Gaussian Process Regression with input-dependent noise (Sigma)
Hi Rick, Incorporating input-dependent noise in a custom covariance kernel is a sensible approach. For a custom kernel, gradi...

3 years ago | 0

| accepted

How to model noise-free case and to obtain Covarince matrix after performing Gaussian process regression using fitrgp
You can set 'Sigma' to a small value and set a name value pair called <https://www.mathworks.com/help/stats/fitrgp.html#input_ar...

3 years ago | 0

LogLikelihood for Gaussian Process regression (function: `fitgpr`) for given set of hyperparameter
Hi Pankaj, Loglikelihood is not calculated for 'FitMethod','none'. As a temporary workaround, there is an undocumented intern...

3 years ago | 0

| accepted

How to specify this mixed effects model?
I am guessing the data looks something like this: >> tbl = table(); tbl.Time = repmat(repmat((1:5)',2,1),2,1); tbl.Su...

3 years ago | 0

| accepted

How to do stepwise knots selection based on AIC/BIC criteria in Linear mixed effect model?
Hi Mithun, You can access model criteria for a LME model via the <https://www.mathworks.com/help/stats/linearmixedmodel-class...

3 years ago | 0

How can I incorporate spatially correlated data into linear mixed effect model which is fitlmematrix method I am trying to use?
Hi Mithun, One way to approach this problem would be to use fitrgp but with a kernel function that combines Z and R. So if yo...

3 years ago | 1

| accepted

NaN confidence intervals from fitlme()
Hi KJ, Have a look at the 'StartMethod' name/value pair: https://www.mathworks.com/help/stats/fitlme.html#namevaluepairarg...

4 years ago | 0

Use of fitrgp to solve simple example (Rasmussen book)
Hi Jose, Function fitrgp fits the model by maximizing the marginal log likelihood. In some cases, there could be multiple loc...

4 years ago | 1

| accepted

Estimates from Gaussian Process regression (function: `fitgpr`) for given set of hyperparameter
Hi Pankaj, You probably want to use 'FitMethod','none' in the call to fitrgp. For more info, have a look at the doc for 'FitM...

4 years ago | 0

| accepted

how does one specify a nested covariance pattern in fitlme?
Hi Ben, The specification "(Pitx*DV|animal:APxML)" above has only 1 grouping variable - namely "animal:APxML". So 'Covariance...

6 years ago | 0

fitlme "Index exceeds matrix dimensions."
Hi Bruno, This doesn't look like the intended behavior but it is difficult to say why you are getting that error. Could you p...

6 years ago | 0

| accepted

How to use the gaussian process regression function in matlab 2015b ?
Replace xd and yd by something like this: xd = linspace(0,10,20)'; yd = fun(xd) + 1*randn(20,1); Rest of the code rem...

6 years ago | 0

How can put random effects in the formula of Fit linear mixed model?
Have a look at the examples here: <http://www.mathworks.com/help/stats/fitlme.html> You can use "categorical" to work with...

6 years ago | 0

Kernel custom problem firgp
Hi Miguel, The error that you saw is reported when the gram matrix is close to singular and the noise variance converges to 0...

6 years ago | 1

how does one specify a nested covariance pattern in fitlme?
Hi Ben, Look at the example titled "Split-Plot Experiment" at: <http://www.mathworks.com/help/stats/fitlme.html> Does t...

6 years ago | 0

How to use the gaussian process regression function in matlab 2015b ?
Hi Regis, Here's how you can reproduce the doc example: % True curve. fun = @(x) x.*sin(x); xx = lins...

6 years ago | 0

| accepted

Calculating the matrix K at test inputs after training a Gaussian Process with fitrgp
Hi Umberto, There is an undocumented way of calculating what you want. Here is an example: rng(0,'twister'); N = 100;...

6 years ago | 2

| accepted

Discrepancy between ANOVA and fitlme
Hi snj, I noticed the following three differences in the call to anovan and fitlme: 1. The call to fitlme should use restr...

6 years ago | 3