Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 8 years ago.
Improve this question
I'm learning about multilayer perceptrons, and looking to tackle some real-world problems in Matlab. Perhaps something like medical diagnosis, or speech recognition... But I'm not really sure where to start here. How should I tackle this?
Geoff Hinton is the man when it comes to multilayer perceptrons. His Science paper from 2006 used a special class of MLP called an "autoencoder" that was successful in digit recognition, facial recognition, and document classification (all of which have real world applications):
Reducing the Dimensionality of Data with Neural Networks
Fortunately, they also published the
Matlab code.
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
There's two things I don't know how to do about them.
I trained the network with alexnet, it couldn't converge. And there was no overfiting. However, when I trained the network with lenet, it converged. Why is that?
I trained the network to solve a problem. It converged, however not enough. The softmax loss can't be lower(0.2). And how can I deal about it.
An inability to overfit may be caused by a lack of network capacity or a bug in your code itself. Are you training the model from scratch? Did you write the model yourself? Are you working on a task at a similar scale to Imagenet classification?
Plateauing of a loss is to be expecting during any kind of model training. But without any learning curves showing the loss across epochs, a loss of "0.2" is meaningless.
Without knowing the exact task your're working on, the framework you're using, source code, learning curves, and/or any debugging steps you've taken, nobody will be able to really answer your questions. I suggest you go back to the machine learning basics in the cs231 lectures (particularly Lectures 4,5) or Andrew Ng's Coursera course for a more rudimentary knowledge.
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 7 years ago.
Improve this question
I am studying J. Schesser's work about HRV in ECG signals.
I am waiting for his answer to the case but also others' opinions and reviews. He has used Labview in most of his ECG data analysis.
I am thinking why, since much of my known electronics do not limit me there. I can use Matlab too.
I want to study time and frequency domains in HRV analysis of ECG signals.
I am mostly using Analog.com's electronics in my ECG boards and systems so they should not be limited to proprietary frontends like Labview.
Why Labview is used in some analysis parts of HRV?
I think it is mostly for NI's LabVIEW Biomedical Toolkit
http://sine.ni.com/nips/cds/view/p/lang/en/nid/211023
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 7 years ago.
Improve this question
my project is to count White fly in an image using matlab, I'm new to image processing so I don't know where to start from , I searched for papers about the topic but I could't find anything useful , my question is to help me start from a point and if you can suggest some papers can help me , thanks .
There is a lot of research in this area, but not specific to Matlab. Try using google scholar to search for papers with "computer vision counting" or similar keywords.
Richard Szeliski also has a very good, free to download textbook on Computer Vision which could be helpful: http://szeliski.org/Book/. Topics like Feature Detection, Segmentation and Recognition might be useful, depending on your exact problem.
When you have an idea of what you want to do, have a look at Matlab's Computer Vision toolbox: http://au.mathworks.com/help/vision/index.html
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 9 years ago.
Improve this question
I'm performing fault analysis on induction motor considering sag and swell. We have a set of data for all types of sag and swell and our analysis includes healthy/balanced supply.
What are the inputs, samples and targets to be considered in building neural networks and how to train the network in MATLAB.
If your matlab installed neural network toolbox, here are plenty of examples that you can learn from.
Closed. This question needs details or clarity. It is not currently accepting answers.
Want to improve this question? Add details and clarify the problem by editing this post.
Closed 9 years ago.
Improve this question
I have tried manual detection using LS polynomial fitting here. But that cannot be used in my project as mine has to be a fully automated system.
Take a look at the Scale-Invariant Feature Transform, or SIFT. This video explains it well. You "train" a detector with one or more images of eyelids, and the detector locates similar regions in the input images. It's the de facto general purpose feature detector - although more specialized tools like face detectors are faster.
The "Scale-Invariant" part means that it can detect the same object at different sizes and rotations.