Below is an interactive demonstration of a competitive learning network.
The network consists of an input layer with 49 units, shown below in a 7x7 grid, and a layer of 8 competing units, each fully connected to the input layer. Thus, each competing unit has 49 incoming weights; they are also graphically depicted in a 7x7 grid, to mirror the input configuration.
Training patterns:The model is trained on a set of 8 patterns. The default patterns are a set of bars of different orientations. These patterns may be edited using the mouse.
Activation rule:When the network is presented with a training pattern, the units in the competitive layer compete to respond. Only the unit whose weights are closest (in Euclidean distance) to the current input pattern is activated, the rest are turned off. The activation level of each unit is represented by the color; the distance of each unit's weights from the input is shown numerically.
Learning:The network learns by repeatedly presenting a
pattern at the input layer, activating the unit in the competing layer who
wins the competition, and then adjusting that unit's weights so as to be
closer to the input vector. To train the network, click on
animate; learning will continue until you click on that same
button, which will now say stop. The amount each weight
changes on each learning iteration depends on the learning
rate parameter, which may be clicked on to have its value changed.
McMaster students: please report any difficulties with this software to
your instructor.