Explore Courses Blog Tutorials Interview Questions
0 votes
in AI and Deep Learning by (50.2k points)

I know how the algorithm works, but I'm not sure how it determines the clusters. Based on images I guess that it sees all the neurons that are connected by edges as one cluster. So that you might have two clusters of two groups of neurons each all connected. But is that it?

I also wonder.. is GNG a neural network? It doesn't have a propagation function or an activation function or weighted edges.. isn't it just a graph? I guess that depends on my personal opinion a bit but I would like to hear them.


This thesis deals with GNG-clustering and on page 11 you can see an example of what looks like clusters of connected neurons. But then I'm also confused by the number of iterations. Let's say I have 500 data points to the cluster. Once I put them all in, do I remove them and add them again to adapt to die existing networks? And how often do I do that?

I mean.. I have to re-add them at some point... when adding a new neuron r, between two old neurons u and v then some data points formerly belonging to u should now belong to r because it's closer. But the algorithm does not contain changing the assignment of these data points. And even if I remove them after one iteration and add them all again, then the false assignment of the points for the rest of that first iteration changes the processing of the network, doesn't it?

1 Answer

0 votes
by (108k points)

Growing Neural Gas (GNG) is shown as a variant of the Neural Gas algorithm, which blends the Competitive Hebbian Learning with a vector quantization technique to accomplish learning that retains the topology of the dataset. The Neural Gas network is a vector quantization model identified by N neural units, each one linked with a reference vector, connected. When an input is obtained, it induces a synaptic excitation identified by all the neurons in the graph and causes its adaptation. For more information refer to the following link:

If you wish to learn about Neural Network visit this Artificial Intelligence Course.

Browse Categories