Where can I find examples of applications for trained ART and SOM networks?

In summary, the class discussed neural networks and how to create an optimized model based off of training data.
  • #1
eoghan
207
7
Hi!
I attended a class in neural networks and I learned something about ART and SOM.
I learned how to implement the learning algorithm, but then? I wasn't told how to use the trained net! I looked in Google and I didn't find much, everybody talks on how to train a neural net, but nobody says how to use it after the learning process.
Do you know a place where I can find examples of (simple) applications of trained ART and SOM?
 
Technology news on Phys.org
  • #2
Er, it should be trained on its application, shouldn't it?
 
  • #3
Yes, I was given a set of data and I was told how to train the net for those data. Now that I have a trained net for those data, what am I supposed to do? I mean, what can I do with that net?
 
  • #4
eoghan said:
Yes, I was given a set of data and I was told how to train the net for those data. Now that I have a trained net for those data, what am I supposed to do? I mean, what can I do with that net?

What kind of data are you working with?

Depending on the data and the application, the idea will be to create a neural network that is able to to create some kind of internal representation of a system that should converge to the represent the actual output itself.

If you are trying to create for example a clustering or classification model, then what happens is that the initial data will 'train' the network to create a model for taking an input and classifying either in an unsupervised form (clustering) or in a supervised form (classification) so that with that model, you can feed in some input and the network will classify it according to how it was trained with the training data.

The classification of data (unsupervised or supervised) helps not only for learning but for the identification of patterns. By creating the right classifications (supervised or unsupervised) you are finding patterns and you can use this for learning either in the network, or in another application (like taking the results of the network and using it in another application).

If the neural network is an optimal representation of the model that you are analyzing, then what this network will represent is the minimal representation of the model in it's most compressed form. Most likely the model will not be an errorless 1-1 representation of the model (there will be likely be errors of some sort), but again the point is that the network itself is a good approximation.

How you actually make use of this depends on exactly what you had in mind when you trained the data and created the network and what the actual data is in context.
 
  • #5
Uhm... I think I have a deep lack of knowledge of som and art... do you know any good book with applications where I can study them?
 

1. What is a Neural Network ART?

A Neural Network ART (Adaptive Resonance Theory) is a type of artificial neural network that is used for unsupervised learning tasks. It is based on the idea of self-organization and can learn and adapt to changes in input patterns without the need for labeled data.

2. How does a Neural Network ART work?

A Neural Network ART consists of two main components: the input layer and the output layer. The input layer receives data from the external environment and the output layer compares the input data to the patterns that have already been learned. If there is a match, the network reinforces the existing pattern. If there is no match, a new pattern is created. This process allows the network to continuously learn and adapt to new data.

3. What is the difference between a Neural Network ART and a Self-Organizing Map (SOM)?

Both Neural Network ART and SOMs are types of artificial neural networks used for unsupervised learning. However, the main difference between the two is that Neural Network ART uses a winner-take-all approach, where only one output node is activated for a given input, while SOMs use a competitive approach, where multiple output nodes can be activated for a given input.

4. What are the applications of Neural Network ART and SOM?

Neural Network ART and SOMs have a wide range of applications, including pattern recognition, image and speech classification, data clustering, and anomaly detection. They are also commonly used in fields such as finance, medicine, and engineering for tasks such as prediction and forecasting.

5. What are the limitations of Neural Network ART and SOM?

One limitation of Neural Network ART and SOMs is that they require a large amount of training data to accurately learn and generalize patterns. They are also sensitive to the choice of parameters and may not perform well with highly complex or noisy data. In addition, these networks are computationally expensive and may require significant computing power for training and deployment.

Similar threads

  • Programming and Computer Science
Replies
1
Views
891
  • Programming and Computer Science
Replies
3
Views
843
  • Programming and Computer Science
Replies
18
Views
3K
  • Programming and Computer Science
Replies
4
Views
1K
  • STEM Academic Advising
Replies
1
Views
1K
  • Programming and Computer Science
Replies
7
Views
6K
  • Programming and Computer Science
Replies
3
Views
1K
  • Programming and Computer Science
Replies
1
Views
2K
  • Programming and Computer Science
Replies
1
Views
3K
  • Programming and Computer Science
Replies
4
Views
5K
Back
Top