Competitive models based on a simple dot product neuron often deal with normalized vectors, which adds a hard computational cost. Using Euclidean distance nodes without normalization is only a partial solution, because they are less plausible from a biological point of view and the computational cost of the Euclidean distance is greater than that of the dot product. In this work the author proposes a dot product neuron, formally equivalent to a Euclidean neuron, which does not require vector normalization. The only requirement for such a neuron model is subtracting from the dot product an iteratively computed bias. A simple incremental learning rule for this neuron is also introduced. The proposed model is suitable for hardware implementation of competitive networks.
[1]
James A. Reggia,et al.
Effects of normalization constraints on competitive learning
,
1994,
IEEE Trans. Neural Networks.
[2]
Teuvo Kohonen,et al.
Self-Organizing Maps
,
2010
.
[3]
Pierre Demartines,et al.
Kohonen Self-Organizing Maps: Is the Normalization Necessary?
,
1992,
Complex Syst..
[4]
Teuvo Kohonen,et al.
Things you haven't heard about the self-organizing map
,
1993,
IEEE International Conference on Neural Networks.
[5]
R. Perfetti.
L1 normalisation in neural networks using parallel automatic level control
,
1990
.