Abstract. The EENCL algorithm [1] automatically designs neural network ensembles for classification, combining global evolution with local search based on gradient descent. Two mec...
The neurons in the mammalian visual cortex are arranged in columnar structures, and the synaptic contacts of the pyramidal neurons in layer II/III are clustered into patches that ...
Christopher Johansson, Martin Rehn, Anders Lansner
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...
Effective backpropagation training of multi-layer perceptrons depends on the incorporation of an appropriate error or objective function. Classification-based (CB) error functions ...
One aim of Meta-learning techniques is to minimize the time needed for problem solving, and the effort of parameter hand-tuning, by automating algorithm selection. The predictive m...