Electronics Letters · 1998 · 35 citations · 5 references
ComputingComputer ScienceComputer VisionMachine LearningDeep LearningNeural NetworksNeural RepresentationPattern RecognitionRepresentation LearningEnergy Function OptimizationHandwritten Character RecognitionInvariant Representation LearningMultilayer PerceptronNeural Network ModelingNeural Representation LearningPerceptronRepresentation Learning Theory
A new energy function is proposed for forming self-adapting ordered representations of input samples in a multilayer perceptron. Simulation results on unconstrained handwritten digit recognition give a better invariance extraction for this model than for several other models.
5
Learning Invariance from Transformation Sequences
Péter Földiák · Neural Computation · 1991 · 683 citations