Community Profile

photo

BERGHOUT Tarek


University of batna-2 Algeria

Last seen: Today Active since 2018

Tarek BERGHOUT was born in 1991 in RAHBAT-Algeria, he studied in BATNA university (Algeria), he received his Master degree in industrial Informatics and manufacturing in 2015 . Also, he received his PhD in the same option from the same university in 2021.
Currently his ongoing research focuses in condition monitoring of complex industrial systems using Machine Learning tools.
Interests : Neural networks; Deep learning; Least squares methods.
Hobbies: Gardening; Photography; Photoshop.

Programming Languages:
MATLAB
Spoken Languages:
Arabic, English, French

Statistics

All
  • Personal Best Downloads Level 5
  • 5-Star Galaxy Level 5
  • First Review
  • First Submission
  • 3 Month Streak
  • Knowledgeable Level 2
  • Solver
  • Revival Level 3
  • First Answer

View badges

Content Feed

View by

Answered
How to build a not fully-connected neural network step-by-step?
you mean like this one, your question is big , i did it once; but i can give you refrences : read about ELM-LRF

2 years ago | 0

Answered
Unknown Future Prediction by Using ANN
I attached this file ,use this function it is great for norlmalization, but befor you normalize your data between 0 and 1 , i me...

2 years ago | 0

| accepted

Answered
Can we change the input size of a pretrained network for transfer learning
yes this methode is cold: 1- if you are changing the neumber of neurons from N to n where N>n: this is called :'constructive...

2 years ago | 0

Answered
I need to know how to add noise in stacked denoising autoencoders. The coding
you dont have to do that, chek my code her it is verry easy: https://www.mathworks.com/matlabcentral/fileexchange/71115-denoisi...

2 years ago | 0

Answered
Hello; nedd help in order to learn programmation
u can use this one here it is very simple (do not forget to leave a comment and rate the application ) Merci. https://www.mathw...

2 years ago | 0

| accepted

Answered
Feature Extraction using deep autoencoder
1) you must create a data set of this windows , dataset =[window1;window2; window3 ...................]. 2) train these datase...

2 years ago | 0

Answered
non-linear dimension reduction via Autoencoder
1) try to normalize you data first, between 0 and 1. 2) use these autoencoders and tell me the difference https://www.mathwork...

2 years ago | 0

Answered
L2 regularization in sparse stacked autoencoders not clear to me
i didnt undrestand your question , could make more clear , there is no k and L2 parameters in the link . could you give us an ...

2 years ago | 0

Answered
How to create Autoencoder whit different input and output
autoencoders are used to this purpose the input must be equal the the target ; this is why they named as autoencoders (they enco...

2 years ago | 0

Answered
Retraining Deep denoising Autoencoder
you will nerver long use the speach frames in the second DAEs, -first: you will encode your input frames with the first DAs. ...

2 years ago | 0

Answered
How are the features obtained in a sparse autoencoder?
in spearse autoencoders , a set of the original images mapped to the output layer passing by the hidden layer, where the output...

2 years ago | 1

Answered
code running for infinite while plotting my array for correlation
if you want to plot Rx , then you should plot B not C, and you can't plot B vs C in this example because C and B they dont have ...

2 years ago | 1

| accepted

Question


How to generate a similar samples from certain distribution ?
I trained a neural net with some samples (images), and i want to generate a new similar samples to the original ones to see the ...

2 years ago | 0 answers | 0

0

answers

Answered
what is meant by sigpara and sigpara1 in code
inside the code you will find the answer; just check the authors definitions of inputs and outputs you will find it there

2 years ago | 0

Answered
I want to predict the fire trend, help me elm version suitable for my problem
it is not about the subject it is about data, you must first look at your data , which type ,is it :'big data or small data', is...

2 years ago | 0

Answered
Imprecision problem: pinv(H) is not equal to pinv(H'*H)*H'
in ELM you should alwayes scale your inputs batween (-1,1) fro both versions, do that and let me know about the results

2 years ago | 0

Answered
Anyone here solves MATLAB problems as 'part-time job' ?
contact me for any problems you want to solve

2 years ago | 0

Answered
How to reduce the number of iterations in partical swarm optimization toolbox?
yes, chane the tolerance value incrimentaly

2 years ago | 0

Answered
how to use op-elm toolbox
first import you excel files into space work using import dat; the save them in the same repertory of opELM as ''filename.txt'' ...

2 years ago | 0

Answered
How to use new learning algorithm for training ANN other than predefined algorithms (like FFBP)
of course you can , this my codes for you: https://www.mathworks.com/matlabcentral/profile/authors/6602421-berghout-tarek?utf8=...

2 years ago | 0

Answered
Accuracy doesnot change by changing number of layers and filters.
try toscale your data between (0 and 1) even thje targets and try a gain , because i faced those problems too.

2 years ago | 0

Answered
How do I represent an empty data in a matrix?
if that data is very important for you , i propose this solution for you: before you train your model , take only the raws tha...

2 years ago | 0

| accepted

Answered
trainNetwork - protect centain layers from changing
yes there is a pssibility take this codes and change the training lope, when you find ''for i=1: nember of layes '' change it to...

2 years ago | 0

Answered
It's possible to export a neural network as a function to use in excel?
i didn' t done it before , but i know that it is possible ; you have weights matrices you can put each one of them in tables and...

2 years ago | 0

Answered
output of neural network
if your network traind for regression : the outputs will be a scaler value correspending to the inputs. if your network traind ...

2 years ago | 0

Answered
How create NN ???
there are 2 hidden layers . but you should know that there is a difference between the training method and the type of the netw...

2 years ago | 0

| accepted

Answered
ELM Classifier does not produce a list of predicted labels
you can just add the name of the output to the function : Y for training output, TY for testing output like this : [Y,TY,Traini...

2 years ago | 1

Load more