Treatment of general structured information by neural networks is an emerging research topic. Here we show how representations for graphs preserving all the information can be devi...
Kernel-based systems are currently very popular approaches to supervised learning. Unfortunately, the computational load for training kernel-based systems increases drastically wit...
Linear Relational Embedding (LRE) was introduced (Paccanaro and Hinton, 1999) as a means of extracting a distributed representation of concepts from relational data. The original ...
Decision trees have proved to be valuable tools for the description, classi cation and generalizationof data. Work on constructingdecisiontrees from data exists in multiplediscipli...
Synaptic runaway denotes the formationof erroneous synapses and premature functional decline accompanying activity-dependent learning in neural networks. This work studies synapti...