An evolutionary approach for optimizing weightless neural networks

WiSARD is a weightless neural network model using RAMs to store the function computed by each neuron rather than storing it in connection weights between neurons. Non-linearity in WiSARD is implemented by a mapping that splits the binary input into tuples of bits and associate these tuples to neurons. In this work we apply the evolutionary µ + ? algorithm [1] to make evolve an initial population of mappings toward the generation of new mappings granting significant improvements in classification accuracy in the conducted experiments.