Comparison With Kohonen's Self-organizing Maps
While nodes in the self-organizing map (SOM) can wander around at will, GTM nodes are constrained by the allowable transformations and their probabilities. If the deformations are well-behaved the topology of the latent space is preserved.
The SOM was created as a biological model of neurons and is a heuristic algorithm. By contrast, the GTM has nothing to do with neuroscience or cognition and is a probabilistically principled model. Thus, it has a number of advantages over SOM, namely:
- it explicitly formulates a density model over the data.
- it uses a cost function that quantifies how well the map is trained.
- it uses a sound optimization procedure (EM algorithm).
GTM was introduced by Bishop, Svensen and Williams in their Technical Report in 1997 (Technical Report NCRG/96/015, Aston University, UK) published later in Neural Computation. It was also described in the PhD thesis of Markus Svensen (Aston, 1998).
Read more about this topic: Generative Topographic Map
Famous quotes containing the words comparison with, comparison and/or maps:
“What is man in nature? A nothing in comparison with the infinite, an all in comparison with the nothing—a mean between nothing and everything.”
—Blaise Pascal (1623–1662)
“We teach boys to be such men as we are. We do not teach them to aspire to be all they can. We do not give them a training as if we believed in their noble nature. We scarce educate their bodies. We do not train the eye and the hand. We exercise their understandings to the apprehension and comparison of some facts, to a skill in numbers, in words; we aim to make accountants, attorneys, engineers; but not to make able, earnest, great- hearted men.”
—Ralph Waldo Emerson (1803–1882)
“And at least you know
That maps are of time, not place, so far as the army
Happens to be concerned—the reason being,
Is one which need not delay us.”
—Henry Reed (1914–1986)