Ruben Van Havermaet's Library tagged "computer science" → View Popular

This project provides Cygwin binary and source packages for a large variety of programs and libraries, including the GNOME and KDE desktop environments.

cygwinports.dotsrc.org/ - Preview

linux cygwin computer science install programs

22 Mar 08

Why Lisp?

nostoc.stanford.edu/...whylisp.html - Preview

ai computer science lisp

true macros, that are
critical when you are inventing a new programming language
most natural language in which to write complex 'symbolic
reasoning'
1 more annotations...
- involves manipulating conceptual
  objects

Self-organizing map - Wikipedia, the free encyclopedia

en.wikipedia.org/...Kohonen_maps - Preview

ai computer science learning

unsupervised learning
useful for visualizing low-dimensional views of high-dimensional data
21 more annotations...
- operate in two modes: training and mapping
- Associated with each node is a weight vector of the same dimension as the input data vectors and a position in the map space
- consists of components called nodes or neurons
- describes a mapping from a higher dimensional input space to a lower dimensional map space
- small number of nodes behave in a way that is similar to K-means
- U-matrix value of a particular node is the average distance between the node and its closest neighbors
- Large SOM display properties which are emergent
- goal of learning in the self-organizing map is to cause different parts of the network to respond similarly to certain input patterns
- weights
- sampled evenly from the subspace spanned by the two largest principal component eigenvectors
- much faster because the initial weights already give good approximation of SOM weights
- training example is fed to the network, its
- Euclidean distance to all weight vectors is computed
- best matching unit
- weights of the BMU and neurons close to it in the SOM lattice are adjusted towards the input vector
- Wv(t + 1) = Wv(t) + Θ (v, t) α(t)(D(t) - Wv(t)),
- monotonically decreasing learning coefficient
- At the beginning when the neighborhood is broad, the self-organizing takes place on the global scale. When the neighborhood has shrunk to just a couple of neurons the weights are converging to local estimates
- any kind of object which can be represented digitally and which has an appropriate distance measure associated with it and in which the necessary operations for training are possible can be used to construct a self-organizing map
- Randomize the map's nodes' weight vectors
  Grab an input vector
  Traverse each node in the map
  
  Use Euclidean distance formula to find similarity between the input vector and the map's node's weight vector
  Track the node that produces the smallest distance (this node is the best matching unit, BMU)
  Update the nodes in the neighbourhood of BMU by pulling them closer to the input vector
  
  Wv(t + 1) = Wv(t) + Θ(t)α(t)(D(t) - Wv(t))
  Increment t and repeat while t < λ
- SOM forms a semantic map where similar samples are mapped close together and dissimilar apart

1 - 14 of 14

Showing 20▼ items per page

Selected Tags

computer science

Related Tags

Top Contributors

Click in to find related links.

Related Lists on Diigo

ComputerBooks

Classic Titles and good rea...

Items: 15 | Visits: 32

Created by: Daniel Eldridge
educational resources

SLIDE SHOWS, CASE STUDIES, ...

Items: 436 | Visits: 45

Created by: Samvritha Sunil
IB Computer Science

Sites that will be useful t...

Items: 27 | Visits: 28

Created by: Lee-Anne Patterson

Highlighter, Sticky notes, Tagging, Groups and Network: integrated suite dramatically boosting research productivity. Learn more »

Join Diigo

Ruben Van Havermaet's Library tagged "computer science" → View Popular

Selected Tags

Related Tags

Sponsored Links

Top Contributors