How to prepare a neural network with multiple outputs.?

08 August 2015 1 6K Report

I have got 36 input variables and 9 output variables. I got 10 samples. I am preparing NN without using any inbuilt function of NN in MATLAB. I want to know whether I have to prepare code in MATLAB in such a way that I need to update weights for every output separately or should I update weights at the time. Which would be a better option?

Vsevolod A Lyakhovetskii

I think it depends on Your task and on the structure of Your network. E.g., for Hopfield network it is possible to use the both principles of weights updating - Asynchronous or Synchronous.

Badges
Science topic

More Ajay Goyal's questions See All

How to apply symmetry boundary condition at one part of assembly without applying to other part?

I am working in LS DYNA. However, my question is general for any FEM based software user. I have two cuboidal parts (one small cube over a larger cube). I wish to apply symmetry boundary...

10 November 2019 3,287 3 View

How to determine a correct statistical test for the mentioned problem?

I got a distribution of variable "y" (unit=mm). Similarly, I have got two more distributions (x1 and x2 unit =mm/s). These two distributions are same but one (i.e x1) is distributed closer to y...

11 December 2018 9,422 6 View

Can automesh command in LS Dyna execute solid meshing?

Dear Friends, I am facing problems regarding meshing of a solid geometry in LS Dyna software. I tried to mesh it with AUTO MESH command. But I am not sure whether it is shell meshing or solid...

09 October 2018 274 6 View

How to convert time domain equation in frequency domain equation?

11 December 2016 3,806 3 View

How to Invert functions with same input variables?

31 December 2015 8,185 7 View

How can I choose effective parameters in stepwise regression?

Dear friends, I got 80 independent variables and one dependent variable with 1000 datasets. I was performing stepwise regression with quadratic fitting. MATLAB memory is showing an error of "Out...

11 December 2015 218 5 View

Naming the multiple line graph in matlab?

I have made 36 equal divisions of a circle in matlab. I want to name the intersecting points as '1,2,...'. Please help

02 March 2015 8,294 1 View

What is the most Operating System (OS) which can be INSTALL on Tiny hard devices like Raspberry Pi (RPi) hardware ?

I'm targeting to deploy a mesh network and manually configure MANET routing protocols. I'm preparing scenarios, architectures, and hard devices needed to do that. Are there some step-by-step...

03 March 2021 1,931 5 View

Is there a powerful system for the security of the systems distributed on IoT systems?

02 March 2021 3,858 10 View

How to choose ANN number of hidden layers and nodes?

Hello, Could you please share any interesting research explaining how to choose the number of hidden layers and nodes per layer in case of regression problems using ANN? Thank you, any help would...

01 March 2021 6,200 3 View

Unknown debris sheets observed in cell culture flasks?

Hi, We culture neural progenitor cells in T175 culture flasks coated with PLO-Laminin. We have successfully grown these cells with our protocol for months. Recently, we observed large sheets...

25 February 2021 3,443 4 View

How to sample data to increase presence of solar panels in the images?

I am working on creating deep neural network on geospatial dataset and wanted to know how to do the sampling so that I can increase the presence of solar panels in the images. I cannot use entire...

25 February 2021 3,936 6 View

Satellite orbit estimation using Recurrent Neural Network - what should I use?

Hello, I am a master's student studying in Yonsei Univeristy, Korea. I am trying to estimate the state of satellite, using Neural Network. Below is a simple flow of my study. 1. Train (t0 ~ t1)...

23 February 2021 6,383 3 View

Any methods to train a neural network with random (stochastic) and non-measurable variable?

Dear scholars, I was wondering if there are any scientific methods to train a neural network or ANFIS when one of the input variables is stochastic (random) and more importantly non-measurable?...

17 February 2021 1,909 3 View

Does anyone know what are the pros and cons for using autoencoders instead of CNNs for features extraction in neural networks?

Are there papers that talk about the possible advantages and disadvantages of using autoencoders instead of CNNs for feature extraction in neural network?

15 February 2021 6,952 3 View

What are the popular techniques for pre-processing measurement data in Smart Grid/Power System?

The data collected from various measurement devices often contains erroneous values - such as noise, missing values, etc. What are the popular techniques for pre-processing measurement data in...

14 February 2021 4,642 2 View

What are backpropagation formulas for residual neural networks?

14 February 2021 4,194 3 View